Beruflich Dokumente
Kultur Dokumente
*C Its IDb
i
fe
Wi "i
iTHEORY OF OBSERYATIONS
LIBRARY
OF THE
UNIVERSITY OF CALIFORNIA.
Class
wm^
THEORY OF
OB SE RVATION
THEORY OF
OBSERVATIONS
BY
T. N.
THIELE
-<>>3i5Kc>-.-.
o! rue
Y
f
'>
UNIVERSITY
Of
PUBLISHED HY
FARRINGDON STREET
LONDON
1903
t4-
COPENHAGEN.
CONTENTS
Numbers
I.
of
Page
formulae
1.
Belief in Causality
2.
3.
Errors of Observations
4.
II.
5.
On
6.
Laws
their Circumstances
Laws
of Errors.
Rei)etitions
of
The Law
7.
8.
of
III.
Tabular Arrangements.
9.
10.
12.
13.
14.
Curves
Curves
11.
IV.
16.
17.
18.
1.
28.
14
Laws
of Errors.
Law
15
16
of Errors
19
Problems
19.
20.
10
11
of Errors
Functional
or Exponential
14
The Typical
10
V.
Curves of Errors.
of
1.5.
111731
20
of Errors.
Series
21
Numbers
Laws
VI.
of
formulae
21.
22.
23.
Page
of
Powers
22
24
27
29
Examples
Relations between Functional
VII.
24.
25.
28-
29.
3031.
30
31
83
Functions of
26.
27.
28.
29.
30.
31.
32.
33.
Functions of
of
Two
47.
35
36
Linear Functions
or
of
37
38
39
Examples
Non-Linear Functions
41
Examples
41
Laws
3846. Laws
37.
Laws
3233. Half-Invariants
36.
Examples
VIII.
Laws
Their Kelations
41
of Errors of the
44
Prediction
34.
4850. Determination
of the
Law
of
Mean Value
is
known beforehand
35.
51.
51
of Observations.
Weights
36.
52 - 58.
52
Free Functions.
IX.
Conditions of Freedom
53
55
56
Examples
37.
38.
Two
40.
41.
42.
Bound Observations
of Observations
6266.
of
to
67.
58
.59
59
59
60
62
63
Can Laws
44.
The
of Errors
Adjustment.
tions ?
6872.
.56
Example
43.
46.
Sum
X.
45.
as free
Example
Every Single Observation likewise
39.
47
50
Examples
Principle of Adjustment
Criticism the Method of the Least Squares
;
67
68
70
XI.
Numbers of
Adjustment by Correlates.
formulae
47.
48.
7381.
8284.
Page
71
72
49.
.'lO.
Modifications of this
73
Method
75
75
Examples
XII.
51.
53.
52.
54.
One Equation
Adjustment by Elements.
Normal Equations
8789.
Special Case of Free Normal Equations
90102. Transformation of the General Case into the Preceeding Special Case
103-108. The Minimum Sum of Squares
85 86.
80
83
84
85
86
Criticism
55.
.56.
XIII.
77
80
94
94
96
98
57.
58.
.'
99
100
103
105
Example
63. 117-120. The Method of Normal Places
Example
64.
Graphical Adjustment
106
HO
112
66. 124125. Laws of Errors for the Frequency of Repetitions. Obliquity of these Laws
65.
of Probability.
119
121
68.
Examples
Use of the Polynomial Formula
Examples
126.
127 129.
for Probabilities
by Repetitions
XVI.
70.
71.
72.
73.
123
123
Oppermann's Transformation
124
126
Examples
118
67.
69.
116
of Errors
129
130
Example
134-137. The Paradox
its
Mean
Error
132
134
of
Unanimity.
Bayes's Rule
134
Numbers of
XVII.
its
Mean Error.
formulae
74.
75.
76.
Mathematical Expectation
138140. Examples
141143. Mean Errors of Mathematical Expectation of Unbound Events
Examples
144-146. Mean En-or of Total Mathematical Expectation of the Same Trial
147.
77.
Examples
The Complete Expression
Page
137
138
139
140
141
142
of the
Mean
Errors
142
I.
We
If
a state of things
Any
difference
by some
is
believed; in the
with which
it
belief.
will,
this
in
same consequences.
part the same, must be explainable
to exactly the
must be
if
must lead
our
it
is
may
It
he
is
closely
may
same way
as
we
be denied in theory,
The law
Any
of causality.
If
we
But
we could imagine
all
if
no one
who
person
If
we must
to
denies
it,
else,
why
the
law
repudiate
all
for
could have a definite number of different consequences, however small that number might
be,
of the
result of
a journey
stronger,
below their
it
But
holds good,
if
We
is
acknowledged
to
when
which always
correctly
appraised
be an assumption
it
would have,
all,
by
if
considering
tiie
cases
in
is
the problem,
observed results
may
means
we must
cell
When, however,
of interpolation.
history.
may
a transmitter of the
still
domain look
difference
moment
same simple,
effects,
as
in
to
the
influencing
causes
the construction of a
single
for
is
operative cause,
living
throughout the
definite,
the physician,
can only
ex-
quite
their domains.
Within the living world, communities, particularly human ones, form a domain
where the conditions of the observations are even more complex and difficult.
Living
For though
munity
cause and
tries to
oft'
as
change one
either to
effect,
give
its
yet
law
divine or
every
fixity,
by
tittle of
any
it is
its
own laws
also.
Every community
and changed.
in the case of communities, represents observations, has
historical
to
An
Observation
is
believe in
we must
and propagate.
it
does not
amount
of sensation
an ob-
to
which are or
that
so
In order that
an
than
law
of
the
difficulty
re-
their effects.
other
assumption
or
by independently bringing to
essentially correct
to conceal,
By
we
answer only a very few questions in cases where the intellectual weapons of
2.
it
threats of punishment;
them alone
bond between
is,
to ask searchingly
observation
causality,
may
it
be
we
enough and
free
from
must include a
get
to
every
perfect
description of
all
is
But
observed.
it
is
we
much
simpler form.
refer to
what
with the observation we, generally, not only disregard everything which
little
which we
the
or no influence, but
call
By giving
known of the
may
be supposed to
essential, because
and
of cause
relation
is
have
effect,
that
observed phenomenon
the
be
will
effect
of these
circumstances only.
to
compelled
disregard
certain
circumstances
as
unessential,
this either
though there is no doubt as to their influencing
because we cannot get a sufficient amount of trustworthy information regarding them, or
because
would
it
be
instance in statistical
impracticable to
trace out
their
connection
with
the
For
eftect.
can
be regarded
And
whether
whether
less
this,
if it
is
certain
that
occurrences.
it is
should give us accurate information regarding both the phenomenon and the attendant
circumstances; but all our senses may be said to give us merely approximate descriptions
of any
phenomenon
recognizes
accuracy
rather
than to
no difference which
is,
moreover,
often
of convenience.
falls
greatly
measure
short
it
of a
increased
accurately.
certain
by
to
the
Even the
finite
use
of
magnitude.
arbitrary
This lack
round
of
numbers
account the odd metres, but certainly not the millimetres, not to mention the microns.
Even our
3. Owing to all this, every actual observation is affected with errors.
best observations are based
is
cer-
influence
tainly wrong, namely, that only the circumstances which are regarded as essential,
the phenomenon; and a regard for practicability, expense, and convenience makes us give
Now and
although
not introduced into them on purpose, are yet caused by such carelessness or neglect that
and ought
more
it,
name
to
originally
still
unknown
For accident
element, involved in
chance)
is not,
to
(or
we
contradistinction to these
When we
them.
say that
it
cleverest juggler
observations
many
know more
we
We
or less.
reject as unessential
may
such a circumstance
if
is
of
sufficient
it,
is
Such
circumstance.
It will
4.
(observational)
very
much on
their
theoretical
theoretical
part
of the science
its
deals
is
reasonings
But
must change
it
its
hypotheses as soon as
it is
The empirical
them
may be
clelr
well developed,
divergence or subordination of
The
(speculative or
is
with
the
theoretical
propositions,
But
it
must not
shown above,
forget
it is
itself
and
induction
By
though
is
it
it
may have
founded on hypotheses.
to
of the observation,
be considered as essential
and taken into account in making the several observations, must not be determined by rule
of thumb, or arbitrarily, but must always be guided by theory.
Subject to this
science should work
it
must
as a rule be considered
somewhat independently
of one
best,
another,
each
in
its
sides
own
of the
particular
way.
it
will be treated
statistical,
chemical, phy-
sical,
they are
rules according to
which
submitted to computation.
all
LAWS OF EEROES.
II.
Every
in
difference,
whether one or several of them have changed between one observation and another.
of the former case, that of repetitions, is far simpler than that of the latter,
The treatment
and
try
is
to
selves
therefore
more
general case in
difficult
its
nevertheless,
we must
By
we understand those
repetitions then
observations,
in
which
all
the essential
circumstances remain unchanged, in which therefore the results or phenomena should agree,
if all
been no such
among
Further-
we assume
circumstance has changed, but do not know for certain that there has
change.
Strictly
speaking,
this
with systematic errors; but provided there has been no change in the care with which the
essential circumstances
if,
it
is
permissible to employ
the records of a
repetitions.
6.
The
special
features
of the observations,
left
and
in
particular
out as unessential
late
their degree of
circumstances,
or
on
Consequently
and particularities of observations.
These
The phrase
'^
the
of errors
is
directly
used as a general
name
other,
Lmvs of actual errors are such as correspond to repetitions actually carried out.
But observations yet unmade may also be erroneous, and where we have to speak hypothetically about observations,
we
titions,
or
have
to
we then
of repetitions
must
some variations
entail
The two
of presumptive errors".
number
In order to pre-
Every variation
in the corresponding
the
in
we compare two laws of actual errors obtained from repetitions of the same kind in
equal number, we almost always observe great differences in every detail. In passing from
if
on examination give us
can be used
its
law of actual
which can
errors,
it
still
measure-
measurements
not every
is
More-
all fell
within the
first
quadrant,
to predict that the future repetitions would repeat the law of actual errors for the totality
of these observations.
or
mis-
conceived, and no law of presumptive errors can be directly based upon them.
7.
still
larger
come more
bound
to
numbers of
repetitions
numbers
each law.
for
we remark
grow
greater,
by
This, however,
is
made under
essentially the
when
it
is
If
at
necessity
in using
for pre-
same circumstances.
to be expected that, if
we could
obtain repetitions in indefinitely increasing numbers, the law of errors would then approach
namely the laiv of presumptive errors itself, and would not oscillate
between several forms, or become altogether or partly indeterminate. (Note the analogy
with the difference between converging and oscillating infinite series).
We must therefore
single definite form,
distinguish between good and bad observations, and only the good ones, that
satisfy the
errors
and
is
those which
above mentioned condition, the Uno of large numbers, yield laws of presumptive
afford a basis for prediction.
As we cannot
we can never be
may
be called good.
on
law of presumptive
we
Nevertheless,
errors.
number
We
and inapplicable, we
that,
to
it
change
why
sometimes by a theoretical
and
of prediction.
series of repetitions
show that
time of observation
A4id
light
if
there to be reckoned
is
we do not
among
errors,
After
is
failure,
and,
sceptic
in
is
The
obvious.
may
at
throwing
for
so,
will generally
time give up
catch
may
doing
phenomenon,
the
whole
himself speculating on
never to be looked for in the objective nature of the conditions, but in an insuffi-
cient development
large
his
remedy
various
we may
failures
repeated
good as
it
many attempts
it
as
not
is
stage, before
criticism
of the method,
others,
when a
of the repetitions,
of
belief.
From
There
this
is
in
point
all
of view
external
then
the
conditions
law
of
such a
parti-
cularly with regard to the essential subordinate circumstances of the case, will be able to
give the observations such a form that the laws of actual errors, with respect to repetitions
in increasing
numbers,
will
show an approach towards a definite form, wliich may be conpresumptive errors and used for predictions.
Four different means of representing the law of errors must be described, and
namely:
Tabular arrangements.
Curves of Errors,
Functional
Laws
of Errors,
we must
take into
is
forms of the laws of errors demands any higher qualification than an elementary
knowledge of mathematics. But we must take into account also, how far the diflerent forms
of the
may
e.
i.
those which
be transferred from the laws of actual errors to the laws of presumptive errors.
may be
As the
presupposes
determination
III.
values
of limiting
to
who
are obliged
to
numerous approximations,
infinitely
TABULAR ARRANGEMENTS.
9.
definition
On
desirable
Identical
results
all
will of course
we
number
of
The
table of errors,
when arranged,
results
and the
fre-
The
number
of repetitions.
are,
It
as
is,
improved,
must be the
number
the
relative
sumptive
errors,
proportion of the
on the supposition of
sidering
infinitely
number
numerous
frequencies which,
of observations
the
when we include
is
Long
is
approach the
in
a law of pre-
number,
errors
an approximation to the
relative frequency itself is the best approximation that can be got from the results
given repetitions,
It
mentioned
is
makes some
if
the
difference
phenomenon
in
is
several
the
of coincident
to
increased,
repetitions.
according to
other respects
Compare
of the
73.
10.
In the former case, in which no transition occurs, but where there are such
abrupt differences that none of the results are more closely connected with one another than
with the
rest,
the tabular form will be the only possible one, in which the law of errors can
9
be given.
is
of observation.
am
it,
and made
of opinion, however,
for this
and
it
demands
All
special attention.
pre-
that
it
is
it
to
the last.
11.
that there
is
If,
however,
there
is
all
is
retained,
care to
at
bring
a
target
may
for
instance
the left
Central
13
Central
foot too
we must take
1 foot to
low
Total ...
4
20
134
26
180
10
On
values,
we
select
values,
we
shall
a table arranged
if,
repetitions.
If,
we
also
we
while
say 16 per
ct.),
deviations.
If
number, and
we may
we
we
is
to
consider these two as indicating the limits between great and small
state these
although rough,
we ought
(b) enter
Why
not to be despised.
we ought
way which
to,
we
is
and
the two sixth-part values for this purpose, will appear from the following chapters.
CURVES OF ERRORS.
IV.
12.
quantities,
we mark
ofl'
constructed as follows.
points corresponding
to
straight
We
of errors
possible.
0,
it
free
smooth
as
If the observation
is
essentially
among
the repetitions,
almost discontinuous.
with
then
this
On
bound
Where
to discontinuous
numbers,
for
If the
observation
made
in
is
somewhat
it
different construction
gives a lower
of the
some in-
and a higher
be applied, viz. such a one, that the area included between the curve of error, the axis
But
in this
involved
in
way
the
free sides
use of round
is
between
may depend
numbers.
This
very
construction
approximately parallel
to the
much on
or
the
of areas
still
better,
If the
11
the
mean
a very
is
common
made
as in 12,
custom,
con-
sufficient.
line
14.
errors, has the
cases
this
critical drawbacic,
form
errors, as a
for
advantage of perspicuity,
would perhaps be
sufficient.
Moreover,
it
the law of
so
in
is
in
many
practice
quite possible, and not very difficult, to pass from the curve of actual errors to one which
may
siiill,
According
to the
for
numerous
series of repetitions,
first
based upon small numbers, afterwards redrawn every time as we get more and more repetitions,
the
curves,
furnished with
which
at
peaks and
first
valleys,
constantly
will
we cannot
of observations,
other.
We may
gradually
last,
become more
when we have
each
other,
as also
finite
number
like
may
be approved as pictures
to the curve of
presumptive
partly by an estimate of
for
errors,
how
for
we must
small numbers
are to
draw conclusions
great irregularities
we may expect
for the
form
of regular
curves
as
as
that sort,
we
of
regular.
In both respects
Without
actual errors,
we
large deviations
feeling tied
that
in question,
cause
to the particular
points that
why
greater
those
down
We
large
will be
errors,
as
n the number
of all repetitions).
^~
,
where
Ave
may
be satisfied,
one third of the deviations of the determining points must be called large.
We
/;
is
the
or three
if
may
only
use
12
the word 'adjustment" (graphical) to express the operation by which a curve of presumptive
errors
determined.
is
The adjustment
(Comp. 64).
Our second
is
ideal,
is
but
an over- adjustment,
called
we have kept
if
too
the
to
close
said to be tinder-adjusted.
somewhat vague kind. The continuity of the curve is an essential condition, but
not sufficient. The regularity here is of a somewhat diflerent kind from that seen
of a
is
we
if
the
of simple,
examples
The curves
acquainted.
circumstances
essential
indefinitely large.
it
in
we would never
of the
observation
so
absurdly
retain
form
select the
the
that
of
which
observation
might bring about discontinuity. It follows that to the abscissae which indicate very large
The curve of errors must have
deviations, must correspond rapidly decreasing ordinates.
the axis of abscissae as an asymptote, both to the right and the
left.
positive, where the curve of errors deviates from the axis of abscissae,
It
latter.
for
must
the
string.
the
must exclusively
In order to train
we recommend
more
therefore
it
the
&
of figs. 2
study
for
eye
3,
the
which
represent curves of errors of typical forms, exponential and binomial (comp. the next chapter,
are drawn from
p. 16, seqq.), and a comparison of them with figures which, like Nr. 1,
actual observations without any adjustment.
The
best
way
to acquire practice in
errors
it,
may
may
be
drawing curves of
errors,
be to select a series
considered
as
which
so important
is
for
which
before
us in
of observations,
is
tabular form.
We
tions;
commence by drawing
the
observations.
On
for
each
small groups
common, and
taken at
drawing we draw
also,
on the same
to be
chosen so that the whole part of the axis of abscissae which deviates sensibly from the
curve, is between 2 and 5 times as long as the largest ordinate of the purve.
of the curve
which correspond
In
pass
on at
last
we must
13
which
is
way
is
means
The following
this
task
table of
as an exercise.
500
results, got
by a game of patience,
may
be treated in
14
The equation
next chapter).
By
the study of
many
form of curves of
Familiarity
deviates
which
is
particularly
considerably
distinguished by symmetry.
it
may become
we
so glaring that
are forced by
we have not a
to say, different
this conclusion.
If,
not
for
the
extremes,
so
that
the
curve of
series of repetitions
proper,
but a combination
results
In such cases we cannot expect that the law of large numbers will
mixed up together.
force,
observations are
the
to
two or several smaller curves of errors beside one another, there can
that
it
remain in
have considered
errors,
of several;
errors.
of presumptive
errors.
presumptive
But
there
that
skew curve of
of a
errors,
fail
is
important
tions
we cannot
and we had
we cannot
retain
series,
essential circumstances
such observations,
if
When
is
we know
errors,
we
all its
copious-
succeed in interpolating in
the table so found, and particularly on, whether we can, either from the table or direct from
the curve of errors, by measurement obtain a comparatively small
which
By
or by
we
number
of constants, by
interpolating, by
means
the logarithms
of the frequencies
as
ordinates,
succeed, as above mentioned, in giving the curve the form of a parabola of low
often
make use
maximum
distance
is
inflexion
almost rectilinear.
we
on each side of
By measuring
it,
near
which the
the co-ordinates
of the
15
draw a curve of
With
cannot operate in this way, and the transition from the latter
meantime
to
depend on the
Laws
of errors
be represented
may
is
expressing the
results.
in
differs
circumstance that the curve which represents the errors has been replaced by
tical
methods, to maintain a
is
so close that
is
it
difficult,
principal instrument.
ideally
errors
of
of these two
of errors
the
is
Its source is
the
in
mathema-
between them.
strict distinction
its
when we speak
to
we
tlie
V.
17.
to
All this,
From
good observations.
is
observations in
order
to
it
these the
remains
to
formula for
determine
how
probable results.
Such investigations have been carried through with a high degree of refinement;
but
it
The study
in this
The representation
must
constant
differences,
argument,
counter
is
is
and
the
that
we cannot
for infinite
one
is
e.
this table.
the results
function,
law of
of the
which
errors.
We may
repetitions)
the
gives
here be content to
proceed by
frequency
difficulty
arguments must be
to interpolate,
rate, increase
0.
We
much
faster
the
we en-
must
of
formula of interpolation,
out to be inapplicable;
any
(i.
interpolated
infinite
therefore
employ some
but
its reciprocal,
itself, y,
will often
become
artifice,
of these
and an obvious
arguments, and
will,
at
16
we have
But, as
it
of the frequency,
to the logarithm
when we apply
Log y
assuming that
-\-
^ cx^
hx
-\-
gx"",
-\-
where the function on the right side begins with the lowest powers of the argument x,
and ends with an even power whose coefficient </ must be negative. Without this latter
condition the computed frequency,
0,
and
its
logarithm
oo
like
few of which
,?;
-j- co
or replace
select
to
As a
finite
rule
frequencies,
possible
to
succeed by this means. In order to represent a given law of actual errors in this way,
we
it
arbitrarily.
number must be
we have
g,
whose
which
deal.
to
Here
also
is
of presumptive errors
pressed by a small
18.
of
And though
number
it
log y
can be ex-
this
supposition,
of x,
Among
is
of
this,
a, b, c,
a troublesome business.
so obvious that
is
nevertheless,
is
it
Log
2/
a-\-bx
a function
is
cx^,
law of
errors,
and
or
he-^\)
/dO-""n-^)
=--
(2)
where
^
the
for
frequencies
/(,
and as zero
and unit n
The
2-71828.
all
for
the
be interpreted
may
observed
values;
the
has applications
in
mathematics
which are almost as important as those of the exponential, logarithmic, and trigonometrical
functions.
its
importance
is
many good
so
great
that,
it
has
as well as actual laws of errors that are not typical, yet every student
though
17
so that the general function resolves itself into a product of three factors, the first of
is
which
constant, the second an ordinary exponential function, while the third remains a typical
recommended.
this
form to
but this
"';
form cannot be
e-''
is
preferable,
The
differential
D^e^lU)
coefficients of
-(,j;^
to
are
3n''a;)e~TW
(4)
D^e"
2^1
X>8g-
The law
numbers)
is
(^)
coefficients
+3
5w*
Sa;^
(products of odd
of D'e
2\n)
2Vn/ and
3 5n^) e'^i^)'
numbers
and
binomial
m)''
(3),
m^ and
as
n^iy+i^
Inversely,
we obtain
xip
x'-ip
x^f
x\
x^<p
a;Y
(p
the numerical
oti^
n- 12 (a^e -^ bn^
arguments.
obvious.
It
(x'^
numerical
of the
of the coefficients to
series,
= w- "
a;
for the
n^Df
='
/)+'
+ +
(
1)
D^<p
0.
= n^D^f
= n^D^f 3n*D(p
= n^D*(p + Gw^-DY + 3wV
= m1Z)55p 10wZ)Y 15w*-^f
= n'^DY + \bn^''D*<p + '^bn^D'^f + 15nV
= 2Vn/
coefficients
-\-
n^tp
of these
(5)
By means
formulse
every
(4).
= D{xTip)-{-rx''-^f.
18
exponential functions and functional typical laws of errors can be reduced to the form
K<p
c^f-
^-^Df
where
<p
+ 11 i>V - ^ ^V +
easily be differentiated
IX
my
e~'i\n'l
(6)
and integrated.
can be reduced to
f\ (x) e
solved
f.j{x)
vir)
-|-
numerically by aid
jy
e"^'\
of the
following table
of the
its
typical
or
exponential
integral \rjdz.
19
Here
jy,
dH
'^\,
-r^
are,
The
means
of Taylor's theorem
..=,
(7)
and
The
and that
always positive,
the frequency has
its
it
arranges
maximum
value
ij
itself
For
h.
is
z/
=A
the
will be
nh 0"85562
nh
creases
e~~i'^
is
toward
= 0,
if
only
falls
from
ct.)
all
which
is
a;
the other
of the inflexions,
either
In
z>b.
almost
all
the foundation
= m 4^
is
w,
nh l/2;r
consequently
of the
rule,
errors.
of the
applications
practical
theory of observations
but also
one asymptote to
outside
The area
of inflexion.
shows how rapidly the function of the typical law of errors de-
table
zero.
it
The above
of
0-60653.
2;
^j^ oo
itself
is
its
the differential
all
the
sum
of equidistant values
This
of e
If the
1
sum
into
curve of errors
is
1.
V2n can
be
computed
not
quite correct,
the
show
far
as
intervals
this error.
Problem
dz
2'' multiplied
2'^
must be
"^^
1 /x m\2
he''~2\'~ir) ,with
form
How
do the constants
h,
20
Problem
the
mean
2,
How
small
are
Problem
3.
To
errors exceeding 2, 3, or
4 times
Answer: sn+i
\x''e
2\
dx.
J 00
and
$2,
(2
1) 9r"+'\/27c.
power
of
error,
19.
the frequencies
number x
of the term.
"
21
w, r,
and
Mi)fin-t{r)
which means
we
consider
when
that,
the trinomial
+ b)-\- c)"
to be ((a
it
{a
(11)
Mr)-fin-r(t),
+ c)"
is
developed,
it
is
whether
indifferent
+ (6 + c))".
or (a
binomial function
x, the
j3{x)
can be taken
sin;:a;
This formula results from a direct application of Lagrange's method of interpolation, and
^,,_
~
l'2., .n
'^"'^^
sin^ra;
.^,
^
~^tor'
(l-x){2-x)...{n^x)
'
This species of binomial function may be considered the simplest possible, and has
some importance
in
it
inadmissible because,
is
for
>n
or
it
negative,
gives
is
may
however,
This,
when X
integral,
^o(^)
As
be remedied.
we can put
/9o {x)
and
1,
for instance
sin Tzx \^
'
TIX
by (10) then
sin^
nx
(13)
l)^
^.(^)
form
is
are ==
tial
[^.
(x\f
+
'
(x 2)V
?r^
0, this
property
is
lost here,
when we multiply by
But
this
coefficients
functions.
These unfavourable circumstances detract greatly from the merits of the binomial
functions as expressions for continuous laws of errors.
When, on
argument, the original binomial functions are most valuable means for treating them.
Pn(x)
= 0,
if j;
>w
But
this case
must be
That
referred
to special investigations.
20.
of errors
in
functional form
we have now
22
the formula (1) or
1)
(,a+IJX+yXi+...-XX^''
2)
l/I m\'
I-
y
3)
sum
y
This account of the more prominent
among
we can even
adapted
laws
of
prove that
may
in
As
to the
errors.
We
If
is
our
do not want
at
find
general
series
anything,
we have
too
many forms
We
which we have
we
(14)
l^lh^e-^ri^l
The convergency
of the
least be foreseen.
we can
select the
trustworthy forms with limited numbers of constants, to be used in predictions. And even
if we should have decided to use only the typical form by the laws of presumptive errors,
method by which we can compute its constants. The answer, that the
"adjustment" of the law of errors must be made by the "method of least squares", may
not be given till we have attained a satisfactory proof of that method; and the attempts
we
still
lack a
think,
all
made
to
deduce
it
be regarded as failures.
VI.
LAWS OF ERRORS
curve of errors
All
in a functional
constants
or, generally,
of a law of numerical
of the repetitions,
i.
e.
errors,
errors,
functions
every general
property of a
law of
results.
For,
as
of the
Conversely, any symmetrical function of the values
23
And we must
to
the
express
itself
by
every
such collection
of
be
symmetrical
functions, by which every property of the law of errors can be expressed as unambiguously
as by the very values found by the repetitions.
We
have such a collection in the coefficients of that equation of the " degree,
For
values.
we know these
if
law of
of
errors.
coefficients,
1,
. .
and
of
all
from
the others.
The
With
that
is
Oj,
0.^,
easiest to
is
compute,
sums of
the
the powers.
O3, ... o
we have
So
s>
+ ..^Yol =n
o'^,+ol
o^-\-o,^..^o
<-\-o\+
s,
0";
+ 0^ +
<>
-^
(15)
oi;
may
also be
,o; for
if
employed as an expression
observations to
suitable
the
for
the law
of errors;
it
is
zero
observations
are
small,
as
compared
may become
practically identical,
to express
From
a well
1
known theorem
+ UiW +
ai(u'^
=
^
(1
Oi<y) (1
(1
OnW)
^'^
g^lOg(l O^W)
to every value of
<^i<")
if
10,
we know
vice
versa,
we
the
by
sum
Ur
differentiating
of the powers
of the
the
/-^^"
last
equation,
equation
f^,
^1
24
with regard to m, and equating the coefficients we get
tti
2a2
S]
a^s^
-\-
s..
(16)
na
-[-
a_i s,
-^"-t
'<'>
from which the coefficients are unambiguously and very easily computed, when the
able collection
But from the sums of powers we can easily compute also another serviceof symmetrical functions, which for brevity we shall call the half-invariants.
these can be defined as
by the
equation
M,
+
^^
s,e\^
^0
so^f
power of
T,
we
7'
-t-
the
get each
first
S3
term of (17) as
e'''^
e''^^
Shrt and
expressed as a function of
So(A:i
i-
12
|2
13
13
(17)
r.
+ t^' + t^' + --
'
^'
II
jl
By developing
+ ...6'"'^
(18)
//j
(19)
+%!/'.+/'?)
(17)
we get
... =
f.+|.'+|^ +
i.g(.
s,
i^jr
So
So r*
+ i^V+i;i + ->
,
(20)
and hence
s.
(s,s
s^):sj
(S3sj-3s,s..9
(s, sj
- 4s,
of the
s, sj
relation
(21)
2s;):.9j
3s', si
+ Us,
between the
fi
s] s
and
- 6s;)
s is
sj
more
easily
understood
25
S4
(22)
/^l
+ %2
'^2
+ 3/^3
+/.4
''l
s,+fr
|r^+|r3+...
all
''O
+ |r'^ +
+
(/.,+|^-r+|r^
equations
can
r,
...)(.s-+^r
...)(23)
values of r by (22).
SqC
affects only
^ij
==e
li
}?.
Tliese
in
the
From
(18)
we
get
+...-{- e
(24)
0'
-|- c,
any change of the
same manner, but leaves fi^, /ig,
fi,,
any
change of the unit of all observations can be compensated by the reciprocal change of the
unit of
r,
^n
"0
'0
We
ratios
'"n
is
so important
in
a law
of errors,
Now we
shall see that it is fully as easy to recognize the typical laws of errors
of their half-invariants.
^2
n'^.
is
that
/^,.
=0
me
m for the
We begin by
we take
while
/x^
=m
and
demonstrated by means of
(5),
quency of an observed x
we
r>3,
if
by means
is
proportional to
(p
(x)
.Sr
of that
e~TV^^/
as this
law
is
get
(+<
iX^(p{x)dx.
fre-
continuous
26
For every
"
(.+
\D'"(p(x)-dx
J
Z>'-V(cc)
(5)
=
=
(22)
Now
3, 18).
we remark
that S2r
that s^r+i
s^
(compare problem
Z)'-i^(
c)
0,
00
we use
we have
0,
but
l-3-n*Sg
1
3 -5
W^Sn
1) 82,-2;
(2r
w''^
= f^iSo
=
Si
fi^So fiiSi
2^2S, =//,,s,^+ /ijSo
S3
%2S2 = /^l3 + S/igS, + /i,Su
4
/is.s
/^i>^5
we
see that
By
is
(17)
we
fi^
^ij
=0
=0
=0
=
==
get
Equating the
if
If
coefficients of
z''
we
/ij
== w,
ii^^=
n'^,
//,
> 3.
If
we wish
change of the
zero,
also
Sr-,-1
The function
if
(p(x)
==
n'^
xr er 'iK"^)
ax
get
is
WAV
+ rw^
Sr_i.
x =<x. and
ijH^
we
{rn^af-'{x
\
^
in)x'')e-^hr),
/
for
00;
27
where
x''e
If
we now from
21
dx.
00
28
we
get,
-S'
and as
/ii
=^ -^
/,)'
The computation
(21),
because s^
the
in
of
and of
As
/i,
y^^^j
/'2-
T^
will
*//!
latter
is
according
by the equation
figures.
There
have no influence at
to (24),
c,
very near
^/,,
all
on
is
com-
[i^,
by this formula
//.,
2s,
^._,.
We
and by reference
select therefore
to
this
zero
the
0\
When
s\
we have
and
u,
s\
'J,
sums
indicate the
Oj
0,
still
... 0
OnC.
and
//',
=//i
c,
then
and
'^
2'(o
have
f,
'^
We
to
nJ
(26)
c)'^
(l^-cY-
is
The square of the mean deviation ^2 i^ equal to the sum of squares of the difference
between each observed value and each of the others, divided by twice the square of the
idea:
''
,
(0,
Ol)^
OJS
(0,
o)2,
(Ol
(O.^
0,)-,
(O5;
0.^2^
Oi)2,
02)^
(0
(02
o)2,
(o
column
separately,
we
find the
sums
(0,,,
(0
On)''
o)^ = Om 2omOB +
and
first
adding each
29
2s, +
2s,o, +
sy,
sy,
o^
o,
2s,o +
2s,s, + s,s^ =
ss,
a,
s.
s,
{s^s,
s\),
consequently,
l'l\or-o,r
The mean deviation
is
(27)
^2slfi.,.
less
less
As
may
being
from
different
zero,
peaked
or
Skew curves
flattened
(divided)
forms respectively by
But we have
In
what follows we
be reserved
from
laws
for
of
errors
the
name mean
"mean
error",
those
to
mean
infinite
to
to
//,
be
and
Thus,
if
= s
Lim=,(//.J
error.
tinuous or to relate
will
transition
when we speak
which
/tr
of the
X.^
is
of presumptive ones.
treat
shall indicate
numbers of observations,
this
are supposed to be
distinction
is
of
con-
course
insignificant.
Examples:
1.
Professor Jul.
Thomson found
we
-],
as
-1
experiments
30
so that
s'
7,
consequently
fi^
s',
= 8,
2650
70
The mean
deviation
is
What
then
is
Answer: u,
have voted
^'
^'
for a
what values
Out of
VI
,
motion
.,
^
^
~\-
either "yes",
is
the
repetitions
in
+ b-\-e
{(a -f c) (a
c against
^'^
ab
inn (n
-r~~
1),
m)
.-c^
'
""
a) {ab
rr-^
which a voters
(0),
and examine
6-)
-\-
Sea -{-be
c)
(2a
b'')
'
(^+ Ff^P
c)2
when one
b + 2c) -{-6{a
n}*
is
to
is
fi
.j
yix
a, b,
and
c,
be == 0,
and consequently
without a being ==
^, //g
=
^=/4 =;U5
0,
but
are
/i.^,
e,
/iu
1,
0.
What
0, 0, 0, 0,
b-
b (a-\-
e)
Answer:
VIL
4tnn-\-n^)
tnn(m^
Ua =^
''^^
fi.i
n "no".
the
=^Q,
"yes",
+ ica + be
(a-f 6
//j
have given
or
1,
{a^b^ey
only satisfied
4.
which counts
c
'
..
3.
mn
==
(-|- ]),
and
for a, b,
2649.
8\2
70;
3.
consequently
1 =
s',
In
2.
and
hiAv
of
errors,
+1.
The
makes
it
impossible to write
in
my
I shall
it
by the half-invariants.
31
But even
if
am
sure
laws of errors, but even the curves of errors and the tables of frequency are too important
and natural
to be
have
therefore consider
it
felt it
my
duty to explain
to
the frequencies
e' +...
and
to the functional
law
of errors.
If in the equation (18)
ne\l
some
of the
o,'s
\l
it
o,
is
of course
is
repeated.
+ "
e"''^
must
I^(Oi)-e~\i''^^'^ "^F""
"*"
i:^
(0,-)
e".-^
(28)
where the frequencies y{oi) are given in the form of the functional law of
continuous laws of errors the definition must be written
eii
we know
if
Thus,
half-invariants
^12
+18
.U(o)eio
may
be found.
If,
Example
1.
"
(.+
\
(f
(o)
do
V/2ff
then
it
may
be possible also
(o).
*/ ''~"''Y
InJu and
\f{o)e''^do
=
=
and consequently
we can perform
X,-,
zhAe
Ehe'"*'
2ii,^
+ -r'\e--A
do
n,
For
(29)
_
then
U(o)e'-do,
we know the
inversely,
if
errors.
do,
32
By
difficult
mi,
iii,
tions
as functions of the ^
of a
sum
only a
if
(or
fi.)
it is
not
compute the
to
results in equa-
of
is
in question.
2.
Example
What
we
2et^+t^'^'t^'
+-
^(0)
The
write
(l+^T.
consequently
(/^i-|-)r+^^r^+^|r='+.--
= '^log cos
Here the right hand side of the equation can be developed by the aid of Bernoullian
numbers into a
Hi
and
"2
^/jr+i
powers of r, consequently
(r>0)
0,
further
n
A'a
^"4
Example
'
^^4
3.
this
^"
What
From
we obtain by
are
'
/^e
= ^n
>
/^8
17
Tg"
'
</)")?
Here
^ nqe-^
we
^^
31
^ ^'
by further differentiation
putting r
/^lo
get
np
^2
npq
{p+if
npq(pq)
(p+qf
33
^'
lp+W\\p+ql
npq
4.
Example
but this
is
b''
==
is
ip
+ qr
ba''.
.Spe-'M +6e'"''
V-
-i^e^'"''
fp(r).
j7-
side of (18).
ra
hand
left
8py( j>-g )\
((p-iV
-Wp+q)
a geometrical progression, ^r
Here the
IP+W'
b^
e^'"'
-|3
+ ...l
and has
and the
rjnr
^r
T--r
\nr
\r
It
is
perhaps
the
to
superior
^BnivWd"--.
'^^
|m
'
law
binomial
as
representative
of
of errors.
Example
order
that
are
5.
while
0,
even
half-invariants
are
.(0)--(i + (f)+(|)' +
Example
irrational
values
6.
Xir
of
odd
Show
2a.
/2r+l
25.
As
0,
/,,
replaced by
r2'
"4
in
for the
J
have
T2U' ^8
5'5'2'
(6)
(p(x)
-)
in
where
half-invariants
the observations must be integral numbers, and that for the relative frequencies
all
proposed
all
IX m\^
= e~~i\^l
34
Now
is
it,
By
(29)
we can
we
and vice
versa.
get
+
se[L'
fc,,
''
'^'
Y^(k,<p(o)-^^^D,p{o)
+ ^-^D^f{o)...)do,
|2
where SQ
..
'^e"''
which
<p
{o))
demonstrated
easily
for
C"^"
l/o-m\2
Y^ D' e-2\-ir) do
1/0 !\2
C"*""
{ zYY
*
00
-^[-ir]
do
(- rfw
-^
(xY
regard
if
\e'''
to
o = i
oc
(f[o)do,
we
only,
,,1',^
l/2;re'"^+T^.
00
Consequently, the relation between the half-invariants on one side and the coefficients k
of the general functional law of errors on the other, is
A;oeTl'+^''-'!l"'+-=(A:+|-r
If
we
write here
>(',
==>!,
and
}!
.,
= k^ m^,
to
A;,-
for the
s,-,
and
)!
and
may
+ |r^+|r...)- +
),
for
It is easiest
In this case
we
get
to
put
m =
X^
and
A-,
=0,
k^
k,
k,
k.
The law
=0,
k.^
n"^
=kf^X^,
We
errors
of
/i.
m,
set
(30)
made by
or
=
k^
it
must be con-
fixed arbitrarily.
X.^.
^kX^,
k. =- kX^,
and further
^ kAK +
= k,{X, + 3bX,X,)
= kAX, + b6X,X, + 3bX])
'^OXl)
35
by half-invariants in this manner the explicit I'orm
Expressed
of
equation
(6)
is
+
+
l+^((^-^)'-3^(x-/,))
1
(31)
>i.
VIII.
There
26.
relating to
have the
to
is
like property,
expressions
for
such
stances,
prima
valid.
facie equally
owing
to
rise,
multiplicity;
to
It
all.
is,
Compare
24,
consequently,
not
Example
others
unknown circum-
summary
the
is
common
to
a manner
none of the
which cannot be
6.
difficult to
single observation.
o.^
is
univocal,
of one
of the
and
in
the
With
Oi
are different,
we can have
be added together.
to
respect, however,
=f
/"(o,)
and
(Oi),
little
in this
of errors
laws of errors when expressed by half-invariants or other symmetrical functions are not
influenced by
it.
The ordinates
discontinuous values;
in the functional
but
law of
the same
is
of the
curves
the abscissa
errors.
In
o,-
for
/"(o,)
as
for
o,-,
and therefore
also
the
replaced by
/"(o,),
it
is
the
36
In the form of symmetrical functions the law of errors of functions of observations
be computed, and not only
may
fore
compute,
for
know
if
all
In
latter.
of the powers
s'
The
s'g
= s^
Sy, s',
functions by half-invariants.
It is
sums
sufficient
if
the
we
if
f{o)
= o^
for
then the
= s^,
s'
is
it
at last
etc.
is
principal thing
cases
For instance,
from these.
directly
m = 2m
only constantly
27.
and
as
sums
when we know
if
/ii
o'
ao-\-h
a//
(32)
etc.
;j.'r
a>r (>!)
For the linear functions can always be considered as produced by the change of
both zero and unity of the observations (Compare
However
to
(24)).
may
be,
(32).
we always
this
in
in practice
is
owing
to
manage
a
happy
about that we are but rarely, in the neighbourhood of equal roots, compelled to
employ the formulae for the solution of other equations than those of the first degree.
brings
it
to
fact
that
we may suppose
the
that
errors
we may
c,
in
good observations
generally in repetitions
so
near
them
all
that
may
0,0^
be
left
0,
The
method, in such circumstances, for transforming any function f(o) into a linear one
m=
The law
of errors then
(^
f(c)
+ f'{c)-(o-c).
becomes
ifio))
f(c]
+r
(C) {[I
(0)
c)
/-(/i
(0))
37
But
functions
also by quite
into
J_
c-{-(o
is
If
_
c)
io
28.
With
that
we should
have,
may
for
It is
still
speak of
we must
we may also,
closely what we
quantities
define
more
in,
and
law of errors
o',
a series of
Om
Oj,
Now
more observed
o'.
it
makes a
difference
if,
common
among
the special
to observations of the
We
different series.
we
'
o'n o\,
to
X
''-
0,,
But here
--^if^Ao)-o)
speak
circumstances by o and
c'
^-M-
(I)
c)-'
of
then
in case of repetitions,
_ J_ _ J_ _
c-jo -c)
c^'
artifices
instance f{o]
for
are led to mistake the partial dependence of observations for the functional dependence
of exact
shall
quantities.
repetitions of different
propose
to
designate
these
interdependences
particular
of
any misunderstanding.
Among
all
But while,
repetitions of
pieces
cast
in
the
one another, and likewise one dimension measured once on each piece,
two or more dimensions measured on the same piece must generally be supposed to be
bound together. And thus there may easily exist bonds which, by community in a circumstance, as here the particularities in the several castings, bind some or all the repetitions of a series each to its repetition of another observation; and if observations thus
connected are to enter into the same calculation, we must generally take these bonds into
account. This, as a rule, can only be done by proposing a theory or hypothesis as to the
38
mathematical dependence
between
the
the
treatment
right
under
falls
and
observed objects
this is
their
common
those
circumstance,
or quite
unknown,
be mentioned
will
later on.
then in a few special cases only that we can determine laws of errors for
It is
the
f{o, o\ o",
its
observations
o,
are repeated
.),
any
Oi
Oi,
f{Oi,
for
other
.
To do
separately.
29.
observations
f{o, o\ o",
etc.,
and
If,
o,
the others
o',
common
and
compute
this a
to
of a
o,,
o't,
each
for
value
calculation
...
o",
no bond at
is
may
it
number
and
will
function y,
same way
as
all
which we must
the equally
all
valid
to
try to reduce
values
for
o',
oi
we
for o,
o',
for o",
com-
o" ...
for
be able to compute
sufficient
of propositions
be almost
of
j'th
but otherwise
i,
of the
of the
But while
quantity.
which teaches us
us in what follows,
sum
viz.,
that
o'.
If the
f{o)
same
the
the
into
of special importance
and
enter
to
.),
Concerning
is
each
y's
are
single observed
pute y
for
we need no knowledge
so
...
which
.,
circumstance,
all
for
bonds,
we can
and laws
.),
o"
o',
in
without
to
functions.
and
for
law of errors
<p(o')
for
o',
is
in
given
then
it
is
the
some cases
of
bound observations
we
and
o'
Om
with
o',,
then by the
mn
o',,
o;,,
0=^o-{-o' we
here
we
more
closely,
and there
39
0,
"',.
+ o;,
0,
0m-\-0\, 0m-\-0\,
Indicating by
where
Mr
+ o;,
o,
and
fi'^
7+
T2
of
o',
we
e!i
0^.
= o-|-o',
sum
the half-invariants of
and
0,
o'.
we
get by (18)
Consequently,
if
nr represent
get
ell
eli
Jl
li
finally
(34)
-Mr ==
/ir
H'r
Employing the equation (17) instead of (18) we can also obtain fairly simple
expressions for the sums of powers of [o-^o') analogous to the binomial formula. But the
extreme simplicity of (34) renders the half-invariants unrivalled as the most suitable symmetrical functions and the most powerful instrument of the theory of observations.
More
any bond,
= a + bo + CO' -{-...do'",
we
manner and by
M,{o)
(32)
= a+
MAo)^
b;t,
b';,,
+ cy,^... + dy:'
c//,
d^';'
(35)
ea.
MAo)
+^>:
r>l.
When
we
functions
a linear form.
In
consequence of
generally
this,
the
propositions (34) and (35) acquire an almost universal importance, and afford nearly the
whole necessary foundation for the theory of the laws of errors of functions.
Example
1.
mean
error
is
for
differences
of the
n^"^
40
Example
viz. the time,
t,
A^iJ*)
;rj.)
/^i^;
1.1.10.14
2
"*
2.
By
when a
But
as
it
t -\-
p {p
when the
f cosec p.
The mean
Example
in
= polar
sin
distance),
very meridian
quantities,
from the
f,
may
known value
we observe two
star is covered
70^2
4n-2
we always
is
one quan-
error is
3.
making marks on
scale is constructed by
such a way that the square of the mean error on each interval
objects,
it
is
we determine
at regular
=
the
intervals,
/j-
distance
of each
object from the nearest mark, the square of the mean error of this observation being
How
is
great
the marks
mean
the
error in a
measurement, by
we use?
X, (length)
Example
good
(^2
1)
4.
Two
how
is
the
Ki^)
5.
>?,-!- 2/;
mean
a',.
The
great
measurements of
Example
is
equally
in
J?
2.
is
the
mean
Example
6.
in a plane
^An
Ji, J^,
J;i
J^
mean
+ Jl + J]
--.
ji J,
error
of the
angle
41
7
Examples
trianglff
and
\ (d\
to transform
pensable
2/^
of
resulting from
combination
the
where a or b ox d may be
difficulties.
of all
sum
Sr indicates the
both
o'^
is
of the
its
and
oC")'',
sum
the
and
it
repetitions
being
0), s^P
Sr
Of
+ A'\.
J'
(
for
the
if
method
possible to indicate a
it is
Thus
k, (quadrangle)
Al);
means
oW.
sums
of the areas
30.
determinations
Even
8.
ksa
.s'j
s^P
(including
the
1.
the
mean
M,
value
SkSa
Jlf,
=n^n\
s't
. .
sP.
and generally Sr
s^s'^,
consequently
cumbersome form
Example 2. f]xpress
mean deviation
exactly
=x''-\-y^,
if
x and y
are
Here
^oir'')
So(^)o(/)
^4 i^) o (y)
= ss\
oo'
and
(''
Here S^
of
/'>
cases
'>
Example
sum
for
of all
If
+ ^s^
{x) s^ (y)
+ So {x) s,
[y)
and
//2
31.
in
/U
W+
fi, (y)
+ 2 {x)y +
+ ^iMAy)l^Ay) + 2(/., (ii)r +
4//3 i^)f^i (^)
(/i,
(o,
itself.
+02+...0)
of proposition
(35)
is
known
half-invariants
>ij,
k^,
..
43
repeating observations and parts of observations,
so
and
this
to be
is
or with peculiarities
the
mean
done espe-
which lead us
to
though with
the
less certainty,
coefficient of
of errors
if
for
any
but also,
only,
provided only
is
throws
it
peculiar,
to
is
all
the observations
all
o,
o',
...
if
it
(35)
are typical,
o<'")
And
From
is
the law
are not typical, then that of the linear function will deviate relatively less than any of the
observations
o,
o',
... Om-
>
= o-{-o'
for
The inequation
Ar
is
if
Ar
and
0'
more
where
briefly
is
positive, r
When we
r*"
it is
evident that
B\
>
(U -\- ly
(5
{U-\-ir.
Remembering
that
(c/r-f
1)'',
f/'
and
^
a;
-f
U-yf
j;-
>
+
if
2,
U-\-U-'
Consequently
(T
>
ir
XU
U, so that
> R\
it
is
x>0,
easily
we
demonstrated that (T
ir =S (K
-\-
If
+ 2'-2>{U^+
-{-
form,
this involves
(!)'
T>
> 2.
But
&^
or
o'.
C/"V.
+ 1)'
or
>
44
and
^^
(>ir
K
but this
is
the proposition
^,
we have
+ V _
+ r,v
^'r
for
asserted,
(ir(0)r^
(A.(O)r'
the extension to
causes no difficulty.
But
must more
thus becomes
if it
or less
general law
that
the
approach the typical form, the same must hold good also of
all
mode-
rately complex observations, such as those whose errors arise from a considerable number
of sources.
of errors" is
employed
to indicate
circumstances which
undeniably influence the result, but which we have been obliged to pass over as unessential.
If
we imagined
is
now counted an
observation would
occur as a function, into which the subordinate observations enter as independent variables;
and as we may assume, in the case of good observations, that the influence of each single
source of errors
typical form
is
which
this function
small,
its
may
be regarded as linear.
if
we knew
The approximation
to
the laws
of
of errors
lost, simply because we, by passing them over as unessenmust consider the sources of error in the compound observation as unknown. More-
we may take
over,
it
for
every such
source of error as might dominate the rest will be the object of special investigation
if
The
calculations.
result then is
and,
removed by corrective
that great deviations from the typical form of the law of
among
or
32.
of repeated observations.
discovered
1889,
Sp s^
I
.
.,
cable.
expressed by suras of terms of the form o\o'\o"*; these are here directly appli-
In
W.
up
to the
10* degree
will
be found.
Up of the rational
Hirsch,
tables
equations 21.
given others
in
Their
of the Sp to
use
the
is
more
coefficients
45
have computed the four principal half-invariants of n^
p. 489).
mk^in.^)
m^/l.,{fi.,)
m'^l.ifx.,}
^h
= (w l)H, + 2m {m 1) X]
= (m - l]H^ + r2m {m - 1)H,L, + 4 (m - 1) (m - 2)^J +
+ 8ot2(w<
= {m l)^;^ + 24m (m
+ 32m (m - (w 2)^5/3 +
+ 8m (m (4m2 - 9m + Q)r, + 144m2 (m l^XJ] +
+ 96m2 (m 1) ^Ul^-z 4' 48m (m 1) A^
(m
l)yi5
m';},(/i,J
(38)
l)'^
l)/l6>i.,
1)
(>w
Here
is
the
number
of repetitions.
Of
/ia
and
only the
tn'n,{/xs)
mnAf^;)
pt^
mean
mean
= (m l)(m 2)^3,
-=
{ni-\y'(}n-2)U,+9m{m-l){m-2y^(XJ,+r,)+
+ 6m
'^
1) (m 2)^^
(m
(39)
and
mUi (/i J
m';._,
(^ J
=
=
6m + 6)X, 6m (m AJ
(m 1)2 (w2 6m + 6)Ha +
6m + 6) (2m'' Ibin +
+
+ 8m (m
1)
(m2
1)
15)/le-<2
1) (m'''
1)
-j-
1)
Further
m*X,{/i,)
m^/ii (//g)
mn^ili-,)
J>1.,
know
=
=
(40)
-|
1',
/I
1)
4-
only that
36m + 36)/ii
30m (m
(7m2
60m(m 1) (m 2) (3m 8) ^J
l)(m 6)/l^
60m''(m
( l)(m 2)(m* 60m3+420m'' 720m + 360)^,
630m (m
2) 8m + ^)k^X.>
210m(m l)(m 2)(7m 48>-|-60)/i^yi3
1260m2(m l)(m 2)(m 10)yi3/i^
(m
(41)
1)
1)
1) (>
/}.,
(42)
(jw^
(43)
MU,{fts)
2) 18?w +
10080''' (m
1) (m
l)(m'' 30^4-90);?;.
840wi(7
(44)
(m
1)
/ij
40)yi5;..,
(/''
Some
teristics as the
/x,^,
and
/i^,
/i,
above formulae.
X^
is
= ^i;
indeed no other half-invariant than the mean value can depend on the zero of the obser-
In
vations.
my
of
mean
0*
all
squares
of the (1
3)
r>l.
mean
s)ti>
The
If r
is
degree, in
m 1
factor
is
No
indices.
m2
and,
appears,
term that
is
if
likewise,
if
only
is
an
multiplied by one or
(m
4)
Many
2)
(w
If,
indicate
particulars
... [ni
r)
these
functions
compounds
kUh) T
e
\1
^l(M
I
^'\1
T2
to the squares of
2>l
r\l=^
+-=h--f^j2
mean
errors of
of
fir
we
factorials
= ^4 ^... = 0,
As
as
and powers of m.
fi^
may
be
1'+
=U(o)e^do.
00
same supposition:
(45)
47
This proposition
for the
at our disposal
mean
the relative
the index
ju,
is
large
enough
fir
pis
number
tlien
errors,
are by no
to give us /i,
guessed,
we have
If
r.
If
is of
it
ni of repetitions
be
will
seen
that
precisely
fi^
then
fairly well,
/i 3
and
be
to
if
As
numerical coefficients in
all
as the coefficients
1,
2, 6,
and 24 of
yij
we must presume
^^,
same degree
of increasing
We
m half-invariants
m repetitions.
first
errors for
We
now
;ir's
to be necessary to
of
the half-invariants
decreasing
We
instance
if
(pitch and
need scarcely say that there are some special exceptions to this
= ^'
/i^
toss),
then
).^[ii^)
is
reduced to
33.
X\,
to solve the
which
problem
actual
is
state of a finite
presumed repetitions
predict, by
oracles
means
is
number
it
of observations
an evident
trespass;
is
to
and
For
is
rule.
and against
of presumptive
Indeed
errors.
is
governing infinitely
mere attempt
at
numerous
prophecy
to
The struggle for life, however, compels us to consult the oracles. But the modern
must be scientific; particularly when they are asked about numbers and quantities,
its
right of criticism.
We
claim
that
confusion
The mean value of all available repetitions can he taken directly, without any
change, as an approximation to the presumptive mean.
If only one observation without repetition is known, it must itself, consequently,
be considered an approximation to the presumptive
The
mean
value.
48
must
in the
same way,
as an isolated observation,
be considered
;,
presumptive mean of
^, (fir)-
tlie
repetitions:
/ii
,2
^ ^
{w l)(w 2)^''
(47)
m"
{f^^+j^^mf'')
[m
as to X^,
P.7,
/?8
it
is
1) (w,
2) (j2
to
preferable
\2m + 12)
use the
principalli/ by
we predict
+,^^1/^2/^3);
equations 42
(/^'^
is
44
iinown in
this
way, or by adoption
first
useful,
did
if
functions
to
mean
errors
of observations
by
nay
and higher
the presumed
These supplements
nor
responsibility,
half-
law of
oracles
do the modern
calculated to
20 days, with a mean error of one day, then you would be very unwise, to be
you provided
as of living.
for exactly
20 days; by
so doing
for 21
if
be
often
may
The ancient
computed
which itself belongs
invariants,
errors,
we complete our
sure,
is
evidently
2325
set out
with provisions
may
for only
But
dangerous.
17
be reasonable.
daysor
less.
When
this
may
choose between
its
It
may
be quite exact,
admission and
its
or
partially
or
rejection, as long as
it
is
always impossible to
absolutely
no
itself.
trial of
of actual errors,
false,
we
are
the prediction
by
which
it
49
If the
errors,
we
can,
^j,
...
/{g,
of
ants of a predicted single observation are given analogously to the law of errors of the
sum
Xr
is
Though we can
more difficult, or
far
in the
Xrifli)-
rather impossible, to
make
of k^,
and
X.^,
X^,
it
of general predictions.
Of the higher half-invariants we can very seldom, if ever, get so much as a rough
The same reasons that cause this
estimate by the method of laws of actual errors.
difficulty,
render
it
matter
of
less
to
importance
In determining X^ and
2.
As
exclusively
3.
to
upon
the
Employ the
From what
X^
upwards,
as
rely
is
is
must be:
theoretical considerations.
It is
half-invariants
determination.
precise
rely
X,^,
any
obtain
it
in the multiplicity
law of errors,
and importance of
it is
(2).
evident
its applications.
not only constantly applied when X^, X^, and ^5 are proved to be very small, but
In these
used almost universally as long as the deviations are not very conspicuous.
will
be
made
to
by the
difficulty of establishing
The preference
many
the
for
to
the typical
form by
typical observations
is
it
of the
intensified
p. 140,
0.
As shown
^^5
/^
in
Oversigter"
imaginary observations.
The
coefficients
kr
of the functional
(6))
50
have this merit in preference to the half-invariants, that no term implies the existence
of any other.
This series
* (X)
where ^{x)
k,
g/i^
'..
recommended
results,
the
advantage of
of errors
seem
to
The
scientific
treatment of such variations seems altogether to require a methodical use of the notion of
laws of errors.
series of skillful
other similar laws of errors (Contributions to the Math. Theory of Evolution, Phil. Trans.
V. 186, p. 343).
efforts to
Example
1.
From
more
refined
In
cases
of very
abnormal
14
are
to
be
calculated
the
presumptive half-invariants up to X^ and by (31) the frequencies of the special events out
of a
number
4-708, Xi
of Sg
= 3-895,
= 500
and Xi
new
repetitions.
= 26-946.
You
find
l^
= 11-86,
X^
=4-1647,
X-^
will
51
52
we must expect
io-^,io)r
35.
that
X,(o).
(50)
all practical
we
applications,
shall
work only with the typical law of errors as our constant supposition. This gives simplicity
and clearness, and thus
may be recommended as a short statement of the law of
= Xi
errors,
a^b
and
By
= V^i
expressing the
mean
errors,
mean
we understand numbers
consequently
-p.
same method,
When
Vr
is
as
the
here, according
mean
value
the
itir,
to
,^
mean
to the
according
value
miVi+m^v^
...
must be
+ mrVr
,^^.
is
when we
(37),
total
itself
formula
to the
computed according
which
numbers
latter
compu-
result.
inversely proportional to
same
error of the
its
We
loeight.
if
nir
is
the
in
cases
means
of various
numbers
of equally
good observations.
error, which we
still
It
find frequently
"mean
the ideas
in
the
cases
0-67451/17,
of
error"
the
while
typical
on
the
law
other
of
hand
still
errors
the
error.
it
computation
of
the
mean
error
error as
is
quite
as
the
mean
very
it is
error to serve as
The use
we have
of the
attained.
More dangerous still is another confusion which now and then occurs, when the
expression mean error is used in the sense of the average error of the observed values
according to
except
their
when we
are
to
the
signs.
this
mean
53
error" is
idea
K^
that
is
we
of a square
The only reason which may be advanced in defence of the use of this
some little computations, viz. some squarings and the extraction
which, however, we rarely need work out with more than three signi-
are spared
root,
ficant figures.
FREE FUNCTIONS.
IX.
36.
mean
value and
its
mean
correct
matics.
For
Oj
is
o,
that
we
LAH)
While the
circumstances
=
=
r,^,(o,) -f
r'J,(o,)
R"
[r"o],
+ r^,{On) =
+ rUAOn) =
that
there
(52)
[r-^io)].
(53)
even though
they
derived
are
from
"'
unbound observations.
aB'
the
bound
to each other.
+ bB" =
[(>'
-f-
[r'o]
If
and
bB".
We
can,
at
any
+ br")
(54)
o].
This possibility
must
in
the single
== [roj
[r^,{o)]
'
ViO^ -\-...ro
is
between "results",
bonds
of errors in the
is
More-
we may
it
The
differs
must be founded on a
the computation
over,
of functions
represented by
of errors
try to represent
is
of
them
and which must be given instead of them as original observations. This may be difficult
to do, but as a principle it must be possible, and functions of bound observations must
therefore always have laws of errors as well as others;
only, in general,
it
is
not possible
of errors of the
54
we cannot,
by means
in general,
aE -\-bR"
errors for
and E".
we determined
It
seems
an
the angle
obvious
in a triangle
= X^_{R')-\-k^(R") = -^ +7p2where J,
J',
then
conclusion
^"*
that,
*'^i^ i^ "^*'
as
correct
R'
R'\
the solution
The cause
in the
it
is
With
unbound
equally good
is
1)
6,
same way.
is ^ j(
F)
of this
is,
~-^,2-
R"
Tj
of course,
the co-ordinates of the angular point enter into both directions and bind R' and
But
tliat
together.
2o, + 0o) =
^2(02
^2(03202+0,) =
we
get
6-ij(o)
6^2(0),
but
= 20Xi{o),
= (03 2oj + o,) (Oj 2o, + 0o),
''2(03-302+30,-0,)
03 3o2+3o, Ofl
although
according to which
we
i?2(03
But
3o2+3o, Oo)
;2(08 203+0,)
+ /2(o22o, + 0o) =
12^2(0).
if,
R'
where ki(R')
= b?>Xi{p)
aR'-\-bR", then,
(53a2
O0+60,
and
;2(-K")
curiously
+ 14J2)^3(o) =
402
enough,
aU^(R')
-\-
14>i2(o),
we
R"
and
2oi+3o2 O3,
and from
as
get
the
this
compute
correct
result
X^iaR' -\-bR")
bn,{R").
To
discovered
simplify
Oppermann
that
our
the prohibition
calculations.
We
is
not absolute,
must
therefore
Helmert
is
enable
us to
of typical form.
= p,o^ +...+;>o
= g,o, +... + ^o.
^1(0,),
55
For these then we know the laws of errors
X,{qo-\
[qk,{o)l
L,[<i6\
[2%(o)l,
Xr\qo\
'
<^''
O/
>-
of the law of
means
Xr{F)
[po]
'^
X.,{po\
and
2ab
mean
bound
to
[qo\ were
in
a difference,
is
X^iF)
the
term
containing
[po] and
if
the
consequently
[pqX^io)]
PlqxX.^{o^)
+2V/,;.,(o)
upon
as
remains typical.
errors
one another.
When
for the
r>2.
for
(56)
It
if
=
=
law of errors
this
supposition.
We
respects like
is
(57)
unbound observations,
call
mean
for the
XApo]a
all
them
of
[_qo}b)
error
a'lj^n.m
+ b-'VqH.ip)]
(58)
holds good.
If
If
good
for
one set of
finite values of
a and
b,
it
holds good
for all.
and
each of them
free,
is
inversely.
Example
1.
2.
When
difference
of
Example
the
co-ordinates
free
the
same
will be
free.
Example
is
for
of
every
3.
The sum
diff'erence
or
the
mean
value of equally
good, unbound
observations
56
Example
4.
The
Example
free.
5.
6.
all different,
are
free.
always
Example
37.
In accordance with
it
is
all
also of observations
free.
connecting bonds;
it
is
bound observations may be regarded as free. The conditions on which this may be the
case, must be sought, as in (57), by means of the mean errors caused by each circumstance
and the
coefficients
particularly
Note
respected.
in the
same
If,
same
to
Likewise,
if
direction.
on the other hand, some common circumstances influence the observations in the
and
work as
treating
them
38.
linear,
or
if,
at
as
unbound
is
at
any rate
less
may
which we
of
observations
from fixed values; and assuming that the observations o,, ...
which
all
given,
the functions depend, are unbound, and that the values of ^.^C^i)
Out of the
total
system of
of
o,
on
^'(On) are
functions
all
= p,Oi +
n observations we can
m<n
[po]
of the given
... -\-pnO
arbitrarily select
partial
fliO,
+ anO
[do]
== diOi
+ do
the existence
of other functions
which are
free
We
57
system
[go]
g ^o I
-\-
by
represented
...-{- c/nOn
[ffd/i^]
=0.
of
free
IS
For
It
[{xa
. . .
-\-
[g(xa-^...+zd)?.2]
into a
sum
of the
function
Any
we
system
[po]
[po]
^ z[gdL,] =
. .
now
can
equations
for
equations
0.
in
is
[pa^j]
x[aa ki]
[pdX^]
x[ad X2]
number
-\-
-\-
(59)
...
We
[p'dX^]
0,
all
that
find
z[da X^]
(GO)
of the
be written
may
[p'o]
function
... '}'2[do],
is
consequence
the
addendum
of
x[ao]-j-
x[cia ^^]
such
that
prove
of two
total
zd) o]
-\-
to
in
[do]
must be
[go]
system,
because
[tto]
if so,
sufficient
is
-\-
z[dd X2]
The number
z unambiguously.
unknown
because,
-\-
of these
from
[dak^]
[aaXi],
[adk^],
is
sum
positive, being a
tions
[ao]
X^iOr)
dr,
[ddki]
of squares,
X(0s)
d,
and cannot be
0,
our supposition
contrary to
could,
[do]
be
represented as
function
of
the others.
From
the values of
a;
...
[p'o]
If
belongs
[po]
termination of
identically [p'o]
to
[po]
x[ao]
the partial
z expresses
its
system
coefficients
z[do].
represented
in
by
(61)
and
then
0.
the
de-
we
get
58
But
if
. . .
must produce
[qo]
[fi?o],
Let [po]
functions
[ao]
[c?o]
[po]
[qo]
functions,
we then
if
in
[ro] be
If
in this
and
[r'o]
may
[jP'o]
['"'o]
be the representative functions of the total system of the functions of Oi...o, because
no relation a[p'o]-\-
a [po]
-|-
4- S[ro]
... -\-
we employ
is
-\-
d[r'o]
[p'o]
and [ao]
[i-o\
.
..
[r'o] or other
[go]
of the partial set [ao]
all free
system [ao]
in contradiction to the
n
.
m
[ko]
must be
No
).
other function
Thus
we can
presumed represen-
[rfo]
result in a relation
might
[do].
it
[ko]
.
of
Oi...0n
otherwise
we
o.
^.^(0^)
X.,(on)
distribute
compounded
which
[go]
is
[j/o]
[ko],
which are
of functions is
a reciprocal
first
is
If the
[ao]
and
first partial
property.
would be found
The freedom
.
it
[do],
would
Answer:
^ {o^
+ 0, O3 oJ,
all
etc.
59
39. Like
all
\ao]
from
= d'i+o'i
Oi
to the
system of [go]
system of [ao]
[c/o"]
of
to the partial
o't
...[ko"]
exist
o'a
o<
which
[ko],
is free
is free
relations [ao']
[do']
likewise
this
be carried
to
operation
an
in
the utmost.
to
through
It
is
[ao]
the representatives
[c'o]
[d'o]
which were
all
the
all
till
Such a
[bo],
to
according
[do],
analogous way,
[c'o]
[d'o]
we
as functions
of
example
2),
and
is
call
When we
we
what
are to use in
errors,
of
. .
[d" o],
it
a
= {r:;^
f
'
MJ^+
because
shall
(comp.
and determinants
enter into
here
follows.
the
complete
This
is
we have
+ ^^drr^
^'M
(62)
^[d^d'k^Y['^""l}
[ab'X^]
[ad" X^]
[ao]
aiOi+
[d o]
fi?,o,-f
=-
...[b'd^L,]
like
d".
\[aaX^]^
is
set
is
which
quite
co-ordinates
rectangular
every single
a complete
the observations,
free,
computations of laws of
all
36,
see,
number
smaller
is
we
select
(37),
enough
to
[bo],
can be treated, by
system
partial
representative
all
has the
Their number
of free functions.
and
[co]
one
of
[do]
free of [ao]
free of [ao]
rest.
[ho],
one of
system of functions,
this
[ao]
except tvhen
easy
We
however, that also the partial systems of functions can be split up.
among
between o'[...o'n.
0,
imagine
But
of this.
= [po"]-\-['po'],
40.
system which
sum
the
is
-\-anOn
+do,
0.
8*
60
As
[ao]
former,
[d^d],
we
must be mutually
find by
free,
mean
(o,)
free of ot,
is
o,
errors X^
"'
'
and
=
If all observations
is
i-^
mean
-^
(63)
(64)
sum
which gives
also
a more elegant
not changed by any (orthogonal) transformation into a complete set of free functions.
We
have
sums
is
r^
reduction
error,
all
form to
+---
is
easily
As
o^...o and n
this equation
variables
arbitrarily selected
for instance,
Also here
and of the
is
(66)
42.
the easiest
must
way
select a sufficient
number
The function
transformed
r^ and
,
set.
[ao\,
of functions
and
fix
one by one.
the order
in
which
which
By multiplying
is
the
first in
the selected
this list, is
we
be
function by suitable
constants
to
In this case
these are
This function
is
is
is
list,
we
can,
multiplied in the
of the forin
list is
taken
61
the
still
remaining functions, so that they give up the addenda which are free of both the
and so on. The following schedule shows the course of the operation
selected functions,
for the case
Fnnctions
4.
62
.
=
=
[ccX]--[avA]-[caXy.[aaX]
=
[dcX]-[acX]-[daX]:[aaX]
[b'b'X],
[ftc-yi]
=
[cbXl -[ab/].[caX] [aa^
= [d'b'^,
[dbi]-~[abk]-[daJ\:[aaX]
:
[c'b'X],
[c'c'X]-[b'c'^
- [acX]
[baX\ : [aaJi]
[db'X\
- [6'c'yi] '[d'b'X]
[d'c>X]
[c'c'X],
[crf/i]-[ac?/l].[ca/i] :[aa>i]
the
sums
importance
X^[ao]
be seen, there
will
the products
of
as
they
= [aaA],
X^lb'o]
properly so
the
squares
[b'b'X],
i^[(f'o]
= [c"c"X],
to be carried out, in
ones. (Because
errors
JS
3''<'
degree.
squares
= [d"'d"'X]
for
each of
of
special
are
transformed functions,
[d"'d"'X].
is
known
and with
/(^(oi)
Ooi
VJo
1,
Sums
0-110
1-210
0-1
1
i-J'o,
_4
3-3
6-4
12
17
35
35
35
12
35
"35
T
"Y
_1
7
FJ303-i#O3
3
"3
"35
12
17
35
3 6
12
36
1
36
'35
_1
i
5
1
Fj03-4J^03+fFJ03-iJ^03
be an
10
With symbols
we have then:
Coefficients
36^
to
such a way that the higher diiferences are selected before the lower
Function
"3
the
of the
and k^[d"'o]
The
"35
12
35
2
[c'd'X]
[b'b'X]
[d"d'X] : [c'V'i]
0,
of
computation
mean
- [c"d"X]
of double
The sums
called.
the
[b'd'X]
[b'b'Ji]
of
[<^b'X\
Five equally good, unbound observations Oj, Oj, O3, o^,and O5 represent
Example.
values
are
[d'd'X\
a check by means
is
[bak] [aa?.]
[d'c'i],
[d"d"X]
As
[M/l]
=
[ddX]-[adX]-[daX]:[aaX] =
= [c"c"Xl [c'd'X]-[b'd'X]
= [d'd"X]
[b'b'^
= [d"c"X\, [d'd'X\-[b'd'^.[d'b'X]
= [d"d"X]
[b'b'A]
- [ad?.]
[b'c'Ji],
of the Products
63
The complete
of
set
observations
free
and
the
squares
of
mean
their
errors
are thus:
(0)=
(1)
(2)
o,
=
=
+ J^o,-^y*o,
Vjo,-iJ^o,+l(Vd^o,-U'o,)
J^o.^^J'o,
(3)=
(4)=
VJ^o.-U^o,
J^03
Through
be sufficient
for
this
/,(0)
>i,(l)
;.,(2)
^,(3)
^.,(4)
for
=
=
=
=
=
1
Jq
f
|
70
will generally
computations
with numerical values which are not given in exact form, but only by their laws of errors.
We
compute the law of errors for a given, linear function of reciobservations whose laws of presumptive errors we know.
By this we can
can, in the
free
procally
first
place,
which there
more or
less
data,
problem.
When
exact
than
of the
reciprocally
unknown numbers
each of the
is
as
by
(35),
compute
unknown numbers.
n observed or
sponding
It lies often
known
quantities, perhaps
unknowns
among
unknown
the independent,
not the end but only the means of determining other un-
many
of the problem.
when
Thus,
other,
which are
for instance,
all
we compute
independent
our end, but in order thereby to be able to compute ephemerides of the future places of
the planet.
is
only
limited
validity
when we want
to
of this
determine
view
the
is
absolute
in
exact
mathematics,
it
Of sought
remains valid, as also the employment of the found mean numbers as independent variables
in the
mean value
If
we want
mean
And
to
if,
errors,
some
64
independent unknowns of the problem as we please, we
often
may
succeed in
carrying
unknown
But
free
w""
unknown can
get
an
factor.
arbitrary
mean
the
errors
for
matter how
many
there
can be computed only in such a way that each of the sought numbers are directly
be,
still
n"-
the problem does not admit of any solution through a transformation into
if
functions,
may
coefficients,
even the
parison to
in all its
to
also
examine how
when the
it
with
is
Still greater
gets the transformation into a complete set of free functions in the over-determined problems,
problem,
We
one another, in order to determine their mean numbers, and the discrepancies themselves
must be employed
repetitions,
to
instance,
Besides,
etc.
sum
is
of the
those of the
for
All
detection.
their
But
angles
must come
of a
plane triangle,
of the problem,
forth by
we have not
to do with
the
the
functions
unknowns
as
of the
necessary
must be
selected
to the determination of
the transformation
observations
values ,
for
as
special
for
use.
is
to
be solved.
As we
moment
here that
we transform
formed functions
in
Adjustment,
itself
it
becomes of essential
forth as observations
of actual errors.
X.
4.3.
ADJUSTMENT.
in
5 we
now
or different
65
circumstances.
essential
of the
Without great
observations.
all
if
however,
regret,
we suppose
all
For each observation we need then only two theoretical equations, one representing
its
ii(o,),
But the
other
unknown
mean
its
equations will
theoretical
as
error X^(Oi),
generally
func-
contain
quantities,
The complexity
is
still
great enough
We
must, preliminarily at
ratios,
used in the
far
the weights.
mean
If
the
not,
we
word "criticism"
concerning the
Hypothetical assumptions
But even
further
if
we
Moreover,
suppose
will
it
X,^ {Oi)
are
solutions,
the
the
for these
the presumptive
to
we
problems require a
first
as possible,
all
theoretical
be
to
equations
or
linear
means
^1(0,)
reducible
many
this
to
form.
quantities really
found by observation, on the supposition only that the corresponding mean errors will be
small enough to render such irregularity inoffensive.
In the solution of such
functions of observations
coefficients.
each problem sets of such functions will present themselves, some functions appearing as
given, others as required.
are,
for
now
The
observations,
among
instance,
the
unknown
0,,
now
as
means
the presumptive
quantities
required
for
the
^1(0,);
exact
satisfaction
of the
theoretical equations.
What
is
the forms
==
(discussed above) of
If
we
repetitions of the
.^i(o,)
X^iot)
or,
generally,
/i,[a(o,
oj)].
66
evidently not sufficient for
determination of any
tion
we
0t)],
these
which
-\-
differences Oi
ot
and by
o,
-\-
this
we
we thus
If
may
^(Oi
be
the
to
sum
the
unbound observations,
oi
be solved immediately.
that
also
only
+ "),
mean
to the actual
first
It
theory
fully
...
it
o,
may
is
of
which
occur, in
may
ing the observations leave some of the observations, for instance o^,
may
is
oj.)]
as representatives.
our problem
the presumptive
of the
values
another
if
by our criticism.
X.^ (Oj)
erroneous
ijnow about free functions: that the whole system of these functions [a(o,
0,
^i(Oi),
found beforehand.
is
>i,(Oifc)
ttie
determines
certain
of
others
quite untouched;
the observations,
it
for
instance o.
it
is
is
when none
Even though
it
must
the
is,
in
as such,
all
same way
further
X (o)
(for
instance the
quite superfluous
as
sum
must be replaced by
and then
maintained,
is
the
mean
and
value;
it
in
on
the
test
the
error
The only
possible
we
or
rejection
(a third
result
is
to
impossible
when
are dealing with any real theory or hypothesis), or to be used in the criticism.
In such a test
which we
it
M =
/ii(o),
and
mean
of presumptive
m)2
in
o,
errors
must be
The
67
equation
at
(o
m)'^
/ig
(o)
satisfied,
any rate be so close that we may expect to find ^2(^) coming out as the mean of
If
then
all
of (o
34.
Compare
u)^.
But generally
fall
the
observations
for the
is
can
the
will be
o,
connected
determination
series of observations
made, so that some of the transformed functions of the observations, which must
be
of the theory,
rest
are
dependent on
entirely
it.
is
what we mean by
fully expressed
by a certain number, n
m,
of theoretical
equations which give the exact values of the same number of mutually independent linear
functions, and as we are able, as we have seen, from every observation or linear function
of the observations, in one single way, to separate a function which
of these just
named
system, represented by
is free
and independent
must include
all
it.
flach of the
thus mutually separated systems can be imagined to be represented, the theoretical system by
m,
represent
upon
observations and
all linear
mutually
in a single
way
is
retical system,
each with
its
by means
theirs, in
only,
unbound obser-
many ways.
of this
transformation,
to
give
the
the other hand, every function of the empiric system and, particularly,
tives
which together
vations.
theory
free functions,
its
On
free representa-
the n observations \do\ and, particularly, the observations themselves are during the adjust-
ment
into
changed at
result of the adjustment, D'-\-\d"d\, is called the adjusted value of the function,
all.
The
and may
68
be indicated as
M,...M.
the adjusted
[du],
The forms
values
of the observations
The determination
mean
of laws
values
adjusted value
of errors
mean
the
is
of the
adjusted values
by repetitions.
is
analogous to
mean
limiting case,
values
represented by an isolated, single observation. In general the adjusted values \du\ are ana-
logous to actual
mean
X^(\do\)
smaller
than k^ {do].
X^\d'o}
The
mean
By
ratio
-fj^
is
analogous to
number
the
of the repetitions or
value.
"criticism"
we mean the
the
trial of
or theoretical
hypothetical
the
[du].
According
to the principle of
34 we must expect
the square of such a difference, on an average, to agree with the square of the correspon-
ding
X-i
mean
error,
X^ [du],
[do]
[du])
X^ ([do]
we
get
X^ ([do]
but
as
[du]) =
[do]
[du] =
X^ [do]
X,
[d'o]
[dti]
D,
and
X,i[d'o]
(68)
which, by way of parenthesis, shows that the observed and the adjusted values of the same
function or observation cannot in general be mutually
([do]-[du] )^
We
free.
ought then
to
have
^^^>
X^[do]-X^[du]
on the average; and
the
number
for
sum
if
we must
expect the
mean
to
approach
by
no help
if
we
u)^
{X,(o)-XAu)y
for after the
adjustment and
free functions
to
the
system
its
such as Oi...o.
errors,
in
is
u^ ... u are
immediately
the
not generally
69
the
represented
the
observations:
theoreticallly given
And
the
as
differences of the
= A,.
[ao\
- B'Y
[6'm]
{[ao]-AY
2 [ao]
the
'
>lj
[6'o]
series,
put down
to be
ought
mean
may
=2
for the
We
the latter,
-Ay
the adjustment,
ratios
is
0.
for
cit.
u^
are only
its
same
men-
M)'^
^-A")
only, while
U^
we can
^2 [du]
(o)
Xi
we
(0
m)'
(u)
it.
these two
sums
More generally we
of squares, conse^
call
(72)
[do]
function- or
theory
loc.
special set of
^2 (m)
/?2
scale
(71)
(O
X^ (M)
A^[du] =
m^Vn m.
k,{0)
of the adjustment on the single observation
the
we can
consequently,
then there
quently
If
series,
{[b'o]-B')^
I, (o)
whole
k^ (M)
The
according to
satisfied;
have consequently
^2 (o)
1,
[b'b'X^-]
tioned
on
If
[ft'i'yij]
distinguished from v^
([g o]
(70)
'
to be strictly
error
we can
([b'o-\-Fl_
m^'\/2(n m).
of which
term of the
free
last-mentioned
m terms corresponding
[aak^]
w
m.
must be expected to be
Of course we must not expect this equation
sum
which
of the series
([ao\-AY
/ij
It
= B'
.. [6'o]
(\b'o\
[aw]
>lj
the adjustment
and the
functions
lowest limit
observation
entirely
all;
0,
we
has
its
greatest
possible
value,
is
/{^[do],
i.
viz.
1,
But
if
e.
the
70
and
observations in
for
this
we
case
jo
u)^
get
Even though the scale has a finite, but very small value it will be inadmissible to deWe understand now, therefore, the
1.
pend on the value of such a term becoming
sum
of the
superiority
M)2
{o
We may
part
of the criticism,
the
to
sum
of the squares
m,
criticism.
for
adjustment on
(0
so
L, {0)
AA)
1^2 {0)
(0
the squares
of
=
- M)
m)21
the
must
hip)
from
the
same, or even
its
terms,
numbers of
we may
trust to the
may
ciously applied,
The sum
sum
of the squares
/--^
of the
squares
M)2
possesses
h [0]
other authors have used as the basis of the adjustment, under the
value that
'
when judi-
name
all
of "the method of
. . .
i?
which
X, {0)
The proposition
is
that
the
[c"o^^
observations,
= \d"'u\
\d"'o']
consequently
by
just
putting
for
this
minimum
adjusted
value u.
46.
form
in
is
The
given.
those of the
general
unknown
form, however,
is
unpractical,
are
eliminated,
so
that
it
is
to
and may
some
number than
This
easily
We
the theory
is
linear equations
we manage
as large
the
to get
{^m)
name
as
may
of elements.
be necessary:
This
sort
we may
of adjustment
is
called
some values
of observations
adjustment by elements.
We
71
whose rules
correlates
when
deduce.
it is easiest to
we
In practice
the adjustment by
by elements when
is
first
is
small.
XL ADJUSTMENT BY COREELATES.
We
47.
^ A, ...
= C,
is
expressed in the
equations
[au]
[cu']
rather than too few, and occasionally a supernumerary equation to check the computation.
The
first
made
Let
[ao].,
by
this operation,
by
the
indicate the n
.. \c"o\
and
the adjustment
system of free
this
free
[d"'o],
[^"o]
It is finally
and according
equations are:
= ^^^
hioi)
is
functions.
to (35)
is
let us,
functions;
into
free of
[ao]
>i,
+ ^jJ^ x,[g''o^]
(74)
dr
c"'
.^
gf
\,,,
As
we
{n ^ ^ +
-
and
= A,
[c"u]
= C",
r"
+ ,,
w*
first
and Xil^u]
= ... = l^ \c"u\ =
il'"
C"
+ Y:J^,'r~^ \d"'o\ +
Q"
0,
1
[g'of.X^io,)
(75)
72
Consequently
[ao\-A
\c"o]-C"\
and
^.(o.)-^.(.)
Thus
for the
+ "- + [o-?Q7j) =
^:Nl[aai;]
computation of
all
the
observations,
each of these,
coefficients
(78)
mean
^^(''-")-
the
for
the values
theoretically
errors,
given
functions,
namely, the theoretical value, and the value which the observations would
give them.
The
_
^"~"
o,-
<,,
m]~A
_
-
^'"
[c>'o]-C"
[aaX.y
which are common
its
The
name.
way
adjusted,
by the formula
M.
By
sum
0.
X, (Oi){aiKa
+ c7K,n}.
(79)
and summing up
the
'
[c"c"A,\
from
1 to n,
we demonstrate the
proposition concerning
_;,()
X,(o)
48.
respect
to
It
deserves to
the symbol
/ig.
be noticed that
Therefore
only
the proportionality
is
preserved;
it
we can
adjust
The homogeneousness
correctly
is
if
we know
not broken
till
only the
we reach the
73
{[ao]-A)^
+ ([c"o]-C")^
(82)
_
It
the
h{o)
that
follows
[o-iif
L
correctness
\{aKa
c"K,..)HM^
= n-m \/2{n-m)
criticism
of the
hypothetical
is
unity
The
of the
can,
where
of squares
2^^^ =^(l-f;4),
taken
errors for
We
each group.
for
may,
(83)
for
another
by measurements of
distances, etc.
The
ought
to
criticism
to be small,
has
also
other
means
at its disposal.
whose mean
particularly those
Thus the
differences (0
u)
k^
(o.)
essential
little.
n.
If not,
we
It will
not be superfluous
to
present in
the
here,
also as to the
The schedule
a^u^
-\-
a^u^
^^i'"'3
"=
^4**4
-S
a,M,
-|-
\hu\
=
=
6j,
+ 62M2 +
\cu'\
== C.
r-iM, +C.^M2 +C3?/a +C.^U^
\au\
is
a^ii^
-\-
then as follows:
10
74
The given
A
0,
/},(,
Free functions
a,
ir
c'
K
K
0,
^AOt)
0,-M,
M,
;,(o,-M,)
[60]
^2(0,)
c'
[co]
\h'o\
=3
[c"o]
[c'o]
[b'b'k]
ib'c'X]
[C'6'yi]
[C'c'/i]
[caX\
K,
\b'o]
[c'6'yi]
By
\_c'b'X\
[aaX]
{b'b'X\
A
[ao]
[6'o]-g
[aaX]
ib'b'k]
[c'c'K]
Ui
summary
KliaaX^-]
= C,
C'-r'B
e'{
c'i-r'b'i
[c'o]-r'[6'o]
[c"o]
{ccX\-r\ca^
[c"c"X]
[c'c:x\-rVh'x\
we compute
n%
-\-c'iKci<)Xi{o,)
c"^
i/n
+ K\,
[b'b'k^-\
+ ifV-
we ought
[c'-c'-yi^]
LM
3l/6.
A, \hu\
B, and
compute [r^]
and
it
is
useful
to
Moreover
m,, m^, m^,
u^.
further to
add a superfluous
C"
criticism
[cm]
of:
== {aiKa^b'iKt,
I
for the
[cVX]
c'i
\c.bX\-p\caX]
for proof
C = C-rA
= d yai
= [c6] Y \a6\
Ydo\
= B-^A
= bi^Ui
= [H-/?M
=
Sum
[c"o]-C"
Kc" ==
computed by means
Oi
and
[c"c">i]
'
b'i
{o,-uy:X,{o,)
"
'
[aa^]
B'
as proof.
Criticism
= [baX\
The
1-;,{m,)
c'
Con-elates
>!,(m,)
4
[ao]
/?
Scales
Adjusted values
C"
= A-\-B-\-C,
through the
75
computation of the
free
which
functions,
correct
is
if
only
identical results.
50.
It
is
that
good
The method
it.
We
are often in
want
of
must be made
solve
to
is,
after
think, immediately
is
and
as
far
cannot well be
it
in order
in a modified form.
condition to annex the whole series of the functions that are to be examined, for instance
.
[rfo],
. .
so
[eo],
must take
order
the
that
theoretical
the
of
the
functions;
The functions
finished.
necessary to
mention
mean
And
error.
In doing so we
free functions.
care
[d"'o],
it
must
operation
.
|
e^o]
unconditionally
made
not
are
others
free
the
give
the
precedence to
till
it
is
is
quite
scarcely
B\
C",
[d"'o],
[e^o].
Example 1. In a plane triangle each angle has been measured several times, all
measurements being made according to the same method, bondfree and with the same
(unknown) mean error:
for
angle
jd
1)
A
C
measurement
<>
ti
50
.1
60
0'
5" as the
2.
(Comp. example
of
6 measurements
"
10
2"
..
15
for
and
0-5, 0-3,
the
*'
mean
0-2.
42.)
have been obtained by taking approximate round values from an exact table, from
all
dilierence is exactly
be used for
schedule,
first
all
the
\/-^.
The adjustment
two
mean number
Example
41, 55,
t)
0'
is
of the
term
corresponds to
the
first
and
1"'
degree,
varied
marked
is
3"",
2''
modification
only,
76
^2(0)
12
19
29
41
55
12
1
1
1
12
1
12
1
1
J*
77
The deviations
is
1'4,
+2'4,
to be
220-8 instead of 3
is
also
1/6,
The
for
M,
and
nowhere reach
-m
29-2
19-4
-0-4, -0-2,
0-4,
a,
the squares
4-8 instead of
well.
very
agrees
(3-4)2, (4.4)2^
(5.4)2^
Example
(6-4)2,
^nd
constant
Indeed,
41-0
11-8
9-8
7-8
deviations o
also
T^'
and J*
0,
2,
gives
differences:
its
11-6
The
J^=0,
13-8
0-0,
to
+0-2
subtraction
from
of 0*04
(7-4)^,
_
3 1/6
3.
54-8
line the
would lead
m,
to
taken.
is
6 distances
"si
are measured with equal exactness without bonds.
we
millimeter
scale,
which
is
|.
It
is
recommended
after
displaced
By adjustment we
the
actually to
measurement
of
avoid bonds.
XII.
51.
correlates
most frequent
for
by
Though
as well
as
cases,
ADJUSTMENT BY ELEMENTS.
every
problem
by elements,
in
adjustment
be
may
is
solved
is
therefore
employed
in
both ways, by
The
far oftener
than adjustment
correlates.
unknown
z:
/i
(o)
explicitely
as
78
^liOi)
P,x-\-q^y-\-
... -{-r^z
(85)
where
the
p, q, ...
are
theoretically
observations
All
given.
are
supposed
to
be
unbound.
The problem
is
then
first
to
determine
the
adjusted
values
X,
tj,
...
z,
after
is
known
h{o)
for
of
these
elements
call '^equations
for the
79
(X
everywhere used
we
add,
but
for /is(o));
if
we multiply
get
\(hp-\-kq-\-
lry'
/*,
k,
and
0,
^Ao)
that
is
hpi
so
the normal
consequently,
But
A^2,
4-
Irt
be written with
all
m1
or a smaller
number
of elements.
further,
The
is
free
we can
But elimination of an
leads to
the
latter
functions
p,ii,(Oi)
jOiA,(o,),
elements are
other
But
it
is
all
the
theory.
and
PiXi{ot)pkX,(Oi)
^,{0)
The
coefficient of
element;
it
it
is
hand
we have been
is
parti-
PP
in each,
which
all
as
the
coefficient
of this
po
as
In the same
^Ao)
all
its
by correlates, we exclusively made use of the equations and functions of the theory, we
put
cally
all
these aside in the adjustment by elements, in order to work only with the empiri-
The
of the elements
coefficients
normal equations
in the
The
it is
in
whose equation
is
it
the
it
will
be seen,
for
easy to state.
coefficients
each of them
as
are,
square
occurs.
of the
We
have
mean
refers,
error
are as
sums
for that
l,{o)
the
and
for instance
P.
by
= h po
J
80
The
qp
in
ys
equation.
coefficients outside the diagonal line are identical in pairs, the coefficient of x,
particular equation,
to be mutually free;
if
we must have
52.
these
sums
special
is
for
if
If
now
in
a;'s
instance x's
pq
^Ao)
function
should happen
is
to be free of
ys
function
0.
particular
way
that
all
in the
form
pp
(87)
81
in
many
first
special cases radical changes can lead to very beautiful solutions (see 62).
thing, however,
is
way
computation of them
to secure a
is
in such a
be selected
is
prepared,
in
and
this
The
must
attained.
This can,
we commence
if
x
and which
viz.
PP
X can then be
k^{^)
for the
the other
'
(90)
computation of x,
it
must be
The equation
x-\-fy-{-
..
-\-(oz
PP
(91)
PP
X
The functions
(q-<pp)6
(rcDp)
X
po
become, by this means, not only independent of x but also free of
or of $,
p_
q^ -jpp
multiplied
that
is
written
f
where
po
subtracted from
particularly refers to x.
+ pr
T
y+
will be
by such factors,
for
for
be always applied;
in
hko)
pq
X
PP
0,
etc.
for
If
we
write
(92)
ftf+5.'y+
we not only
get,
as
we
Wo]
X
see at once,
become
.+r\z =
u.,
82
but also
83
With
the equations
elements
these
the adjusted
for
become
and
+ rrc =
pp
we want
tions of
several
observations
(99)
M,.
errors
q'q'
+1^
p,'
If
mean
of the
values
+ .---+rf
(100)
^2(M,)-
compute adjusted values and mean errors for the original elements or functhe same, the means of so doing is given by the equations of transformation
to
+ fy-\-
and the
...
x, y,
+(oz
4-
in
(o'z
last of (98),
For not
=
=
a;
y
z
Now,
operations
and
we
if
is
mean
X^(F)
for
of
9i
54.
In
that
5',
we
the theory
the
summary
sum
(102)
...
/,
get
we want
6'^
the
the
^It fPi^
c^^
computation of
equations
^^(m,) for
= *Pi
r"
which
is
observations,
computing
their
^i
<-'?;;
of
the adjustment by
minimum sum
(0-
many
of observations,
the
...+ ^C
it,
transforming
coefficients by (92), or
we remember
error
4-7-C
c.
a^
special criticism
but
,+
If
...
f+3j-)-
to
know
n m,,
We
are able to
compute
as
the adjusted
84
And
observations.
ment, but
for
this
formed elements,
f,
must be computed by
From
this
we
...
jy,,
get
61-2
^Ao)\
we here
The values
(99)
{o-vf
If
Ci-
substitue for
i-r-
for
q'O
'?!
It is easiest to
show
corresponding to these
85
for the several
The sums
may
observations,
nearly
of the squares,
/i
Mj
transformed
the
first
of
transformations, and
the
r'.
indirectly
also
the computation
for
Only
r^.
q'.
we cannot escape
criticism,
special
but
ones,
the
ones.
original
M of
the
of
^^ (m.)
considerable
often
^2 (")
consequently for a
work which
is
necessary
for
the purpose.
we have
dispense with
seen,
We
of the elements.
the case
is
= n m^V2{nm),
]{ot
hio)
0,-,
Mi,
minimum sum
Add
scales
0,
m,,
when they
when
of squares
certainty, directly
on
means
generally
by
even, as
is
we can
/i^
(m,)
and the
/j (0)
to the
the
more
or less essential
criticism.
theories,
errors;
will
2"
of signs, will
frequent changes
form of a
multiplied
Crelle's
series
which)
errors
Journal
how we ought
vol. 94),
factor,
i.
an
or
to try to
and
e.
J. P.
may, we
number
adjustment
by
how many
Formula (107)
this.
= m^ l/2(w w).
J
errors
ro
h (0)
mere absence of
the criticism
means of doing
(o-u)
[
hypotheses
in
with an indeterminate
defects
some circumstance,
unknown
by an
as a function of
disclose
ill
to indicate
series of
By
or
betray
regular variation in
according to
fur-
For the
terms in the
series,
which
here indicated by
is
we take
unity;
all
into
this,
series of
adjustment.
<
If
1.
we
retain
out
ro
>
we make
if
by about a
we
leave out
2",
if,
fall
ourselves
guilty
of
an over-
upon
as
mutually
adjustment.
The
place.
"observations",
table
is
are
constantly
looked
l/J^
of the fifth
log 795, log 796, log 797, log 798, log 799,
decimal
log 802, log 803, log 804, and log 805, are to be adjusted as an integral function of the
second degree
x'-{- y't
we
2-90309
+ 0-00054
t,
zt^.
-\-
Taking 0-00001 as
2 =
2 =
=
=
=
1
1
=
=
1
1
1
From
this
we
get
36
420
=
=
540=
is
by + 2bz
4y-{-16z
x 3/4- 9z
X 2y
iz
x
-{-
a;
1/+
'^z
a;
x-{-\y+ \z
= x-^2y-\= + 3y+
a;
=: X -^
iy
-\-
4z
9z
I6z
= + 5y + 252.
a:
The element y
132a;
0y+
0a;+1320y+
1320a;
0/
1320^
Oz
23496s.
made
87
free of
it
is
The transformation
we have
first
= x -j-lOz
88
11
is
12
is
x 0-7836 =
sum
3.
ought to be noticed that the adjustment gives very accurate results throughout
with the exception of the beginning and the end. The
greater part of the interval,
It
the
exactness, however,
is
2.
Example
is
supposed
Co-|-Ci cos
r+s,
The
We
not greatest in the middle, but near the 1" and the 3'* quarter.
finite, periodic function of one single essential circumstance, an angle F,
whose
Show
difference is constant
and
-,
n
F=
0,
for
a series of values of F,
that the normal equations are here originally free, and that they admit of an exceedingly
Example
and 60).
Example 4. Three unbound observations must, according
3,
elements, so that
=
=
0,
0,
The
jcS
Aj(o,)
xy,
,^5,(05,)
known a
for
common method
2'"'
degree,
we
o.,
a2) + 26(02 6) =
ab) + 26(03 =
2a(o^
2^
+
,
.,
approximate values
= +
2af
6f
+ ^'y
2h7j,
(4a''
6'^)
rj,
be produced
= +
double weight.
2a(o,
may
ah =
O2
h^ =
still
This
of presupposing
We
o^a^
is
1
-1
x and
=
=
depend on two
to theory,
in several ways,
to
+ 2i)f+2a6)y
2ah f + (46 + 2a2)
jy
are:
but we find
62(52o
2a.6os
+ a2o8)
,
'
(Svfppa^{b^o,2abo^^aHs)
''2(^)
+ 26^
4(a2 +
a'
62)2
,,
2a
+ i
89
For the adjusted value u^ of the middle observation we have
(a^
If
+ fe^M, =
ab^o,+{a'-{-b*)o,+a'^bo,,
^,{u,)
i-
^^J^-
62) by putting
aC ^0
='b^-\-au,
or
free
i(i
+ + o,
normal equations
i{a^J^b^)^i:
2(a2oi
If
we had placed
squares as a
The conditions
of
minimum
5,1/
^ -^j^ =
rfmin
The
a and b
immediately that
(o,-a^)(o,-b^)
OjOg
Still better is
it
to
0^ =
introduce
{o^
s^
b^o^
is
not very
a^-\-b'^,
difficult.
We
a^o.^.
s^)a-\-o,J) =
('-H^)
must then be
A
0.
0,
s*-sHo,-^o,)-\-o,o,-ol
s^
of
{0,-abf
consequently,
two values of
sum
j.\ /.
2abo.^-{-
o^a-\-(o3s^)b
of the
== min.
i,ow =
ab)a->r(o.^b')b
7\
{o^
or
principle
are:
d min
b'')^u.
(0,
a solution
minimum,
2(a''
=('-i^)+";-
large, o^o.^
0-^
small, the other nearly equal to Oi-^-o.^; only the latter can
be used.
12
90
Further,
91
21ogx
results
logo.
^,(logx)
(^,3^j log-^
^^.(J^^.).
for
moment
that, in this
from
far
is
the
repeat
^b
y
it
is
o,-
errors
and
/,
agree,
and we must
only
mean
of the
squares
as also
small.
are
errors of
then
the
till
adjustment
And
values.
might seem
It
o,
is
correct
and
mean
itself,
=2,
the radius
y^
/,
of four
^ 20,
errors
and x^
The co-ordinates
5.
Example
mean
because
obtain
+ {y-b)' =
of the observations
Xi
-\-
of
elements,
we
Ayi
These equations
know
^a
1'^!
for
yt
first
we must
-\-
r sin
we must work by
which the
In order to
adjustment by elements,
F,-
successive corrections
A a, A
Axt
and
Ayt
6,
by
of the
= A a Ar
= A6 +A
cos Vi
-{-
>
sin
F,-
A Vi
+A
F.-
r sin
F,-
r cos
F,-.
makes
it
possible
for
us immediately to discover
the artifice.
in free functions.
The
radial
A Xi cos Vi A yt sin
A Xi sin Vi A cos
-\-
and
3,
the "method of partial elimination" ( 61) these are not difficult to solve, but here the
We
Axi
By
x^
r\
necessary for
r cos F,
= 18;
y^
of the equations
Ar, AF,
x^^ 16,
the separation
As
in
4.
(x-a)^
it
points
= 10;
y.
y,-
F,-
F,-
=A
=A
w,-
<<
12*
92
can,
quantities,
mean
consequently,
values
of corrections of observed
= A a sin A 6 cos F, A Fj
<,
F,-
F,
In this way
^.^in)
k^i^)
k^iiy),
In
the
case
fourth point
6 = 10;
= A a [cos^ F]
[A n cos F]
[A n sin F]
[Aw]
lie
+ A r [sin F]
+Ar
-\-
special
on the
under consideration, we
circle
with r
= 10,
easily see
that the
4.
first,
second, and
= 10
and
Fi
00'0,
F^
537'8,
Fg
F,=
and
1350'0,
21652'2.
consequently,
all
other
0,
<3
a;3
for
0.
yt
a;,-
observations" are
are:
For cliecking
2-5000 A o + 0-4600 A +
A = + 0-0710
0-4600 A a + 1-5000 A 6 + 0-9071 A r = 0-0710
= 0-0929 A a + 0-9071 A 6 + 4-0000 A r = 0-1005.
6
E
By
Ar
elimination of
we
0-0929
get
A a + 0-4390 A 6
B = 0-4390 A a + 1-2943 A 6
eliminating A b
A = +2-3490 A a
+ 0-0733
= 0-0482
==
2-4978
and by
From
jK,
B, and
Aa
The checks
+0-0896.
we compute
+0-0381
A6
0-0501,
and
Ar =
0-01465.
The 4 equations
93
Aw,:
Aw,
Ami
the
(o
sum
(8
=
For
this,
(0-0234)2
is
7)/} 2)
+ (0-0235)^ + (O-OISI)^ =
(0-0319)2
= 00151;
0-00235.
0-01010
0-00236
The 4 equations
AF,
for
AF5,
-4-17'2,
give us
tt
AF3
+20'8,
F,
we have
the
017'2,
F,
5328'6,
definitive values.
In both cases
Ax
0-0232
+0-0191
+0-0166
0-0123
The sum
F3
9-9499,
and
V,
approximation,
21630'6,
+0-0002
+0-0002
+0-0257
0-0166
+0-0320
0-0234
0-0001
0-0090
+0-0152
comp.,
0-0000.
agrees with the above value,
hypothesis
are:
0-0000
+ (A y)^] = 0-00236,
first
At
0-0232
this
if
differences, obs.
An
Ay
who
13457'1,
the next
for
10-0381,
to
= 21'6.
AF,
9-98535,
-2'9, and
sufficient.
final differences,
From
the equations A, B, and R, which express the free elements by the original
bound elements,
A a, Ab, Ar,
we
easily
trans-
formation:
A a = 0-4257 A
A6 = 0-1444 -^ + 0-7726- B
A r = 0-0228 A 0-1752 B + 0-25
By
these,
for
E.
R; and by
yi^C^)
= 2-3490
>i
5,
X^(B)
= l-2di?, X^,
94
and ^2
(J?)
= 4^2,
the co-ordinates
X^(x)
'i2(y)
the
mean
x and y
of the
mean
errors of
are
F)''}>i2
is
uncertain.
XIIL
We
57.
it
tations
lie
as
much
to
means which
as possible, even by
much
this
many who
try to
among
And
as,
moreover,
not the only one that was justified under the given supposition,
it
is
no wonder that
it
has come to be used in many modifications which must be regarded as unsafe or wrong.
After what we have seen of the difference between free and bound functions, it will be
understood
stand out
values.
that
much more
as to
And
of transgressions
the consequences
some
the
in
clearly
mean
errors
against
importance
is
correct values computed for the elements, than to getting a correct idea of the uncertainty,
the lax morals with respect to adjustments have taken the form of an assertion to the
effect
we
that
especially if
can,
we take
within
this
care that a
minimum.
This, of course,
by stating
all
is
domain, do almost as we
sum
wrong.
like,
even
In a text-book
experienced
When
is
which are
difficulties.
to
Only
observed.
first
were used in the computations (logarithms with 7 decimal places), and people often comas an unavoidable evil, when
plained of the great labour this caused; but it was regarded
the elements were to be determined with tolerable exactness.
much
simpler apparatus,
We
if
95
able to
fied:
both
we
the elements
respects
Often
formation.
figures.
seek
can be
it
difficult
free of
enough
The condition
we ought
satis-
and in
we
that
itself
be
to
to protect oneself in
artifices
so called,
is
it
But
learn
know
to
the
of their smallness
is
satisfied, if
we everywhere
use
same preparatory computation as is necessary when the theory is not of linear form.
By such means as are used in the exact mathematics, or by a provisional, more
the
allowable adjustment,
or less
a set of values
v^
several elements
we
corresponding to
get,
the
several
observations
o,
o,
any rate considerable exactness, nowhere show any great deviation from the
and x
?,
corresponding observed value. It is then these deviations o,
x^... which are
or
perfect
at
made
with which,
error
When
common.
in
in
a non-linear theory
the equations between the adjusted observation and the elements are of the general form
Ui
F{x,
.z),
approximation.
first
or by
(109)
of
we
+ (f)(^-^o)
= PiX +
i-iZ
No
tions
0,
Vi =
Xa)^
'Piix
...
putation, and
significant
figures
^o)-
(110)
whose devia-
it
certainly requires
mean
errors, so that
a;
of the deviations
o,-
z,,
lest
is,
as
is
especially
Vi
ought
to be
of
com-
many
computed with
(^
The method
The
''
special luck is necessary to find sets of values, ?;,,... a;^, ... ^n,
Vi
increase the
X^
{ov)
k^
(o).
is linear.
96
by the eye, with tolerable
observations,
ment.
certainty
The preliminary
lead
etc.,
observations
equations,
equations ,
F(x,
w,-,
terms
higher
and
provisional,
in
for
o,-
vt
Where
it
must be repeated
On
which ^^
the adjustment
the values
until
Vi
(o,)
is
generally
of
,-,
to
may
by
got
is
as
be regarded
only
direct
as
computation,
known
till
we
get a sufficient
only as functions
unknown
of the
probabilities,
quantities which
to give us.
is
The form
59.
the actual
possible,
elements,
If not,
approximation.
for
is
series.
Taylor's
normal
the
the
be
to
In this
as in the computation of ,.
of
of deviations
ought
z)
may
of
the adjust-
to get into
falls
we ought not
rejection of such
to the discovery of
of the theory,
determined
rule
all
of the
formulae,
mentioned
reasons
in
the
is
much
it
it
is
also possible, if
same system, elements between which we may expect beforehand that strong bonds
exist.
will
Thus, in systems of elements of the orbits of planets, the length of the nodes and
the distance of the perihelion from the node ought not both to be introduced as elements;
for
will,
is
u=p-\-qt,
= r'\-q{t
tQ),
unless
where
t^
is
all
observations.
and
this
line
two corresponding
t,
latter.
If
the formula
the
change in the
If
comparison
then
we have
97
much
that
the
the adjustment
for
calculations
which
mutually
in
free,
will
by careful selection
in
products [pq]^)
of the
elements,
we even
of the
sum
mean
of the
themselves
then be used to determine the law of error for the elements; we compute
may
sums
of products
0,
and
in
we
[po]
correct
the [j9o]'s
[pq\ y^
....
- [pr\ z, =
(111)
[pp\ x^
while
=
As the
errors
in
these
,s,
t:{M-M-...-M}.
determinations
are
of
the
second order,
it
will not,
if
the
o's
make any
further approximations.
Even
the
if
If
we can
get
new
the
we can sometimes
get
if
we can
some
tions
has
plete
attain
single ones,
may
made
year,
freedom
we cannot only
facilitate
means;
If,
especially as such
for
instance,
And
we do not
')
it,
but also increase the theoretical value and clearness of the result.
we
in
unused observa-
an arctic expedition
little
make use
of the
means
of single observations.
to
[^J.
13
60.
sin
Though
important
of cases,
in
is,
exists, nevertheless,
to use a
depends on the fabrication of such observations as might bring about the freedom of the
As a warning, however,
theoretical elements.
against misuse
give
it
a harsh name:
the
for instance,
viz.
4 points whose 6 mutual distances have been measured by equally good, bondfree observa-
we can
tions,
now
"12
+ 0,3
-|-
Oj4
"12 + + "24
0,3 O23 + O34
''23
Oj,
Oj,
O3,
la;,
i^x^-\-6x^,
lajj
=
which,
if
we imagine
distance ^,(o)
it
^ Xr
to
a;,,
la;,
4-
Iscg
+ 1^4
4" 1^3
as
value of 0,
What
in
this
all
of the
abscissae
4a;2
4a;8
4a;,,
entitles
any
4x,
by means
of
the
us
distances
to
fabricate
observations
while
mean
values,
but also
is
indeter-
When we
and
treat
easier solu-
mean
errors
of a
must be introduced
fabricated observation
of the
elements,
And
we must here
carefully
demonstrate,
by criticism in each case, that the fabrication we have used has not changed anything
which was
really
determined without
it.
99
In
the
the
above
values
adjusted
example,
for
the
Xr Xs,
distances
and
then
disappearing from
O's
by
own
adjusted
the
determine
neither
The mean
nor
it
get any
errors
The
influence on
in such a
the
way that
criterion
let
value,
= 0.
all
as
for,
is
after the
adjustment as well
consequently
method
and
0,
this is
of fabricated observations.
61.
large,
it
The
the elements.
to
Long
numerous that adjustment by correlates could be
indicated, a correct adjustment by elements can become practically impossible. The special
criticism is quite out of the question, the summary criticism can scarcely be suggested, and
before
become
must be made
so
easier at
any
some
price.
If it
the others, then there can be no doubt that the expedient which ought
is
These observations
first
to be
employed
will by this
means be replaced by
and they
certain
will be
so in a higher
this proceeding
of
insist
hand emphatically warn against every elimination which is not performed through free
functions, and much the more so, as it is quite possible, in a great many cases in which
abuses have taken place, to remain within the strictly legitimate limits of the free functions,
is
connected with the cases, in which some of the observations, for instance
do not occur in the theoretical expression for any other of the observations.
then, by the formation of the normal equations to separate o^
observations.
diately
We
perform
.y,
of x,
is
o^ as a special series of
begin by forming the partial normal equations for this, and then
the elimination
which
Our object
imme-
for a
100
As soon
as
is
The trans-
suspended.
formed equations containing these elements (which now represent functions that are
all observations, and functions which
depend only on the remaining elements z,
.
put aside
we come back
till
to the determination ot
y.
The other
free of
m),
are
partially transformed
That
elements x
x'
imagine
P^r then
==
0,
this
all
is
proceeding
quite
the
inserted instead ot
sums
jc'.
becomes
legitimate
is
/',
evident
which are
we imagine
if
free oi
u,
the
and then
become
and the sums of squares and sums of products for the separated part of the observaaddenda in the coefficients of the normal equations (compare (57)), come outi
tions will, as
As an example we may
of 3 points on a straight line.
now
The mode
of observation
The readings
for
as follows.
same row
is
in
We
apply a millimeter
oif
by inspection with
down
of
to
the scale;
the
but these bonds are evidently loosened by our taking up the position
against the scale of an arbitrarily selected fixed origin yr as an element beside the abscissae
1,
101
As the
method
consequently to form
normal equations
for
we choose
If
of partial elimination.
s""
first
is
every reason
Where
we have
O,
Or
=
=
2yi
/i
-\-
Ojj
+ O3
==
Ol
03
Xs
-\-
+ Xr
Xr
is
+ ^i +
+ ^i
3/i
y-'
^^
+ ^3
-\-Xs.
!/i
referring to the
ij,
free
elements
equations from
subtracting these
By
in the cases
the corresponding
0,
i{0r + 0s)=
^X,
= \Xr + \Xs
\{0r-\-0,)
of the equations,
we consequently
'
of these
get,
how
\Xr
ia;., |a;3
1^1 + 1^2 \^i
h^i \^2 + i^-6-
differences
often
|aJi
for
37"71
+ 206-69
'Ix.-'ix^-lx^
= -^x^^-^x^
= -'{x.-'lx^ + '^x,.
-g-a;^
two
-168'^8=
its
we
i(Oi + + 03) =
02 3(01 + 02 + ^3) =
M01 + O2 + O3) =
03
Oi
side
equations
right
other
g^ = ^-f-|l +
|l,
weight
23712
How
is
102
after
168-98
114
U9
37-71
+ 206-69
*i
114
= ^x.
=
consequently,
mm.
Xi
From
these
= 25-38
we now compute
/i
2/2
2/6
We
differences,
for
=
=
=
=
=
==
x^
4-77
and
which
it
is
= + 21-24.
the ys:
33-72
0,
33-27
32-295
2/7
25-945
15-485 0.
,
8-845
=
=
=
y,o=
enough
56-80
-0,
58-27 0,
35-01
45-55 0,
2/1,= 44-29-0.
^3
each column; their squares, on the other hand, will be found to be:
I
nor their
103
As
to
functions are
weights of
easy to
a;,
special
criticism
it
is
the
weights
the
of
eliminated
free
scales
X^(u)
1
1
'
Xi(o)
as
wliere
respectively
compute the
With 759
liere,
common denominator we
2
3
4
5
6
7
9
10
11
"
Weight
after the
adjustment
of
their
104
functions of the original observations, need not always be so iirmly connected with one another
as in the ordinary method. If we, in a suitable way, take advantage of regularity in the obser-
vations,
But
in our way.
in
able, to find
order
free,
out any
to find
special
transformations,
general form of the changes of the normal equations resulting from transformation of the
the
for
equations
have been
+ iiV + r^z,
Oi-^ Vi^
the normal equations will be:
=
=
[qo]
\ro\
And
if
we wish
to substitute
new
{qp\x+{qq^y
+ \qr]z
[rp]x-j- [rg'Jy
-|-
elements,
f,
;j,
and
[r/]0.
(^,
we make use
new
of
ones,
therefore
== /.,f
2/
+ A:,, + Z,C
(114)
[
The equations
Oi
(jo./ii+?<^2+'<-^3)f+{j'.-^i+?.-^2+'.^3)'?
+ qh^-Jrrh;)
[{phi
o]
[(ph^-i-qh^
+ (i't^+9'J2 + n^3)C-
(115)
$ being
+rh^)^
rl^)\ C-
The computation ought not to be performed according to the expressions for the coefficients
which come out when we get rid of the round brackets under the signs of summation [ ].
But
it
is
easy to
give
exactly as if
for
The
old normal
unbound observations,
for
X,
we
y,
and
get the
z, respectively;
new normal
equations, but
still
105
=
=
[{pki-{-qk^-{-rks)p]x
The second
Upki-^qk^-\-rks)o]
[{ph
+ ql2-i-rl.^)o]
new elements
+ [{pk,+qk^^rk^)q]y + [{pk,-^qk^-\-rk^)r]3
[{ph+ ql2-i-rls)p]x-^[{pl,-^
must
for
\{\16}
ql^+rl.,)q]y^[{pli-i-qL,-\-rl.,)r]z
In
order
tj,
now by rows, by
the products,
'11
'3
'2*
Example.
happens pretty
that there
linear measures,
is
irrespective
Already P. A.
into the
mean
the
two
in
terms [po]
pointed
values
on
the
hand
left
^^^
Xmr =^
Of.
(*j.
Sr
Ctr
[ao]
[60]
{co\
[rfo]
+ {do\
=
=
=
=
4a;
3a;
2a;
la;
+
+
3?/
6/
42/
2/
the equations.
}^(xr
a;,_,.).
[bo\ -^{co-\
bx
+ \0y + 10^ + bu =
[o]
.3a;
{bo\
[co] =
la;+
Sy
bz
l2
- 3m =
2y
2z
I2/
\u
In
the form
+ + 1m
+ 40 + 2M
+ 62 + 3m
+ 30 + 4m
22:
+ bu = lO^i^ + lO^i^
5a;
[f/o]
of
as follows:
--=
[ao\
is,
is
sides
out that
Xf
the procedure
for
as the
observed
this case therefore the equations for the old elements by the
sums and
of scales
investigations
Hansen
Sr
instance
for
often,
10 ^^^
+ 20 ^^
6^^+2^^
2
"^^^+4
14
106
As
in
this
as two mutually
differences,
The
63.
titions,
the
in
we always succeed
example,
is
the general
to
when
case
mean
night,
to
to allow
know how
to act in
such cases.
they form
<?,
mean time
of observation
t,
mean
right ascension a,
star at
t.
With
this
is
what
in practical adjustment.
called the
is
are,
connects
place,
by
circumstances, holds good also, without any change, with respect to their
Much
normal
values both for the observed values themselves and for each of their essential
is,
speaking
strictly
mere repe-
are
It
same
the observations
in the
values
When
when
to
owing
mean
the
separating
contradistinction
observations,
in
free
trouble
may
mean
values.
The question
We
shall
first
consider the
tions being:
?.^{o)
With
the weights v
we form
a-{-bx~\-
z,
-\-
the
equation
for
are
linear
the observa-
de.
[vxo]
=
=
[vzo]
[vo]
unbound observations o
where the
case
a[v]-\-b[vx]+
a [v.t]
-\-
b [vx^]
-|-
^[^'Z'^]
... -ird[vz]
'^
[vxz]
(117)
\
(118)
If
the whole
series
of
a\yz^ +
observations
is
+ (^[f^*].
we
place,
shall have:
0,
107
VX
=
=
=
VZ
V
VO
and
[V]
[vo]
[vx\
[vz\
as
= a + bX-^....-J^dZ,
this
normal place
will
we
0)(z Z)] =
[v{o
for the determination of the
if
small
equations (118a)
are
small of the
order.
term
is
least
-^dZ
elements b
determination.
quantities
normal
squares,
if
-{-d[v{xX){zZ)]
second
up the
split
places
if
the
forming
series,
equation
now
lost completely
xX
and z
Z are
for
the observations
according to the
to
corresponding
a)
order,
instead of
(118
+d[v(2 Zf]
d,
of the
still
a-\-bX-\-
elements b
these
adjusting
method of the
b[v(xX)(z Z)]-{-
If,
and
place,
blvixXy]-^
is
first
But
error.
get,
0)(xX)] =
lv(o
(117a)
the
constant
this determination of
d, in such a way, however, that we suffer a loss of the weights for their
This loss can become great, nay
suitable selection of
suit
the
purpose;
but
it
total,
if
can be made
rather
insignificant
by
Let us suppose, in order to simplify matters, that the observations have only one
variable
essential
sequently
>li(o)
x's are
con-
a-\-bx,
a;,
we then
let
each
normal place encompass an equally large part of this interval, and we shall find then, this
being the most favourable case, with n normal places, that the weight on the adjusted value of
the element b becomes 1
11
if by a correct adjustment by elements the corresponding
weight
made
is
still
taken as unity.
smaller,
if
The
loss is thus,
at
any
rate,
And
it
can be
is
108
uneven, and
we can
if
normal place
get a
everywhere where
the
become
observations
particularly frequent, while empty spaces separate the normal places from each other.
The
case
is
For
it
when
is
still
functions of a single
is
and we can do
so not only
the variations of the circumstances can be directly treated as infinitely small within
falls
y =
with the
f{po),
For
if
we
circumstances and
essential
mean
then we
can use mean numbers of deviations for reciprocally adjacent circumstances as corrections
which, added to the corresponding values from the approximate formula, give the normal
values.
that
Further,
the
is
it
within
deviations
is
made
so comprehensive
do
limits
its
the
of
essential
circumstances.
is,
is
and
lost,
it
is
difficult to say
under equal circumstances, smaller, the more normal places we form. With twice
as many normal places as the number of the unknown elements of the
problem,
will rarely
it
become
perceptible.
distribution
suitable
observations
are
of their
sufficient to
know
we have
do with
to
transformations
of
essential
it,
normal places
of the
also
As
circumstances.
to
it
however,
we
is,
as
s^
generally,
rule,
when
functions which are essentially different from these, will try through
the variables
to
get
back
them
to
and
certain
to
functions which
We
need only consider the cases in which we have only one variable essential
degree.
0, and
We
their
to
circumstances, x,
and weights,
v,
determine r-fl
to
substitutive
is
essential
observations, 0,
mean
same
number
to the
method
of actual observations.
of
The conditions
are:
OoVo+ ...+OrVr
j
(119)
[OX'V]
XlOo Fo
+ TrOrVr
109
and
[,]
[x^-'v]
x':v,
Vr
(120)
...+xrvr.
We
unknowns.
The elimination
roots
Xq,
of the
Xr
When
positive.
remove the
are
the
Vs
real
all
are
distributed
where in
that they
to
-\-l,
may be
this interval;
if,
given x's
the
if
quantities,
roots
for the
r+l
degree,
whose
first
uniinowns.
and
looiied
if
upon
further, the
sum
of the weights
0,
2;
mean
error every-
degrees, be
000
o{ V
2-000
'
-577, + 577
'
1-000,
(X
1^000
= -775,
000,
+ 775
-556,
889,
-556
'
'
-348,
\x
= -906, -538,
237,
(X
652,
479,
-652,
348
000,
+ ^538,
906
569,
479,
237
'
661,
932
361,
171
'
171,
361,
468,
468,
000,
6
129,
If,
280,
382,
418,
+ -742, + ^949
406,
280,
382,
is,
lilcewise,
^129
continuous,
but the weights within the element dx proportional to e^^^ consequently symmetrical with
maximum
by
a;
0,
then
the distribution
for
no
X=
^\f=
-000
jX
=
I
X=
V =
fJt
^ '^
\V
^
~
**
loss of exactness.
the
least
number
required
is
-000,
+1-732
-333,
1-333,
-333
+2-334
-908,
-092
2-857,
-1-356,
-000,
+1-356,
+2-857
-023,
-444,
1-067,
-444,
-023
-3-324,
-1-889,
--617,
-617,
+1-889,
+3-324
-005,
-177,
-818,
-818,
-177,
-006
3-750,
2-367,
1-154,
-000,
+1-154,
+2-367,
3-750
-001,
-062,
-480,
-914,
-480,
-062,
-001
now
able
able also, by the use of such tables in analogous cases, to prevent any
would be possible
It
we had but
not possible.
values
of
normal places,
to
form
the
Certainly,
essential
method of
circumstance,
places
but we cannot by
of
all.
them ought
By taking
be determined.
to
corresponding
This,
the
to
a simple formation
to have,
of
without employing
into consideration
how much
extreme normal places from this reason must lose in weight, compared to the sub-
stitutive
observations,
can amount
1;
but for r
essential
1049 to 1171.
tion
0,
we have:
first
estimate
of
r 21 p.
the worst
3 we lose 19,
for r
for
case,
and
c.
Example.
an
we can
In the
to.
to
-742,
-908,
-742,
-092,
the
mean numbers
'
squares;
as
however,
-1-732,
'
we were
we should be
then
1-000
-2-334,
=
=
=
jX
\
If
1-000,
'
(Z==
i
+1-000
'
=
=
=
'
1-000,
X =
/-
2-000
Eighteen
Ill
112
Now, by application
of the
6-72 =
_ 2-84 =
216-00 a
-54=
1-57 =
By the
-2-80
get:
+
1-87 a +
29-45 a
1-87
ft
7-93
ft
1-20
ft
+
+
7-93
c+
1-14 c
1-14
rf
+ 2-45 d.
free equations:
6-72
we
1.20 a
=
=
216-00
+ 29-45 c+ 1-87
(^
113
and
ment
is
drawing
from
irregularities
free
The smoothness
observation.
or extremely intricate
when,
of a
we succeed
to
when
relatively best
we must
for instance,
the
satisfies
two conditions
curve in
the
of
is
it
curve which
performed
of being
and
its essential
by free-hand
the theory
is
unknown
phenomenon must be continuous within the observed region, or be a single valued function.
But also such a theoretical condition as, for instance, the one that the law of dependence
must be
ment,
the operator has had practice in the drawing of parabolas of higher degrees.
if
may
And
we have seen that also such functional forms as have the rapid approximation to an asymptote
which the curves of error demand,
As
for
the approximation
so
make
the
near
the points as
typical form
our
to
figure
all
each
care that
take
side of
If
for
cannot pay
number
the
not only in
it,
its
much
or laws of errors.
errors
In
of course,
regard,
errors,
we
the presupposed
to
but something
may
be attained,
a graphical
the
observations,
there
adjustment, however,
same number
of the
the
of similar deviations.
we draw has
curve
intersect
observation.
must
If
exactness
mean
is
as to the
We
not necessary;
is
the
to
a perfect identity
we know anything
lie
they
may
contradistinction
down on
errors.
and of
to this
it
observations, represented
all
by different points,
it
is
possible
to lay
Around each point whose co-ordinates represent the mean values of an observation
its essential circumstance, a curve, the curve of mean errors, may be drawn in
is
less
it
than the mean error resulting from the combination of the mean errors of the
its
is
make
mean
error.
Evidently,
114
laws of errors both for the observation and for
If the
mean
If,
mean
the ellipse of
distant
the
mean
the
by
mean
the
well
as
errors
and the
errors
is
reduced
to
mean
the
values
the ordinate,
In
are
continuous curves
their
jjnown to be free
is
and
abscissa,
errors.
of the observation
error
means
mean
of the
ellipse
mean
circumstance, then
its
If the essential
of errors,
its
be used.
may
for instance,
If,
mean
the
errors
may
essential
be drawn on
The
and
errors
we can
of the
principal advantages
its
circumstance or abscissa as
its
indication of gross
By measuring
the ordinates
corresponding to as
them
select
as
we
many
values
please within
the
limits
of
the
drawing.
On
with
the other
hand,
interpolations, both
too
much
graphical adjustment
can be
advantageously combined
very
its
defects,
confidence
in
particularly
its
limited
accuracy and
little
its
in the theory,
tendency to
i.
e.
to give
an under-adjustment.
By drawing we
frequently insufficient.
The
is
of a
This
is
straight
And
line.
is
full
lost
if the line
by the
flat
line,
which
eye
it
its
is
scale of the
and that
also,
The
not the original observations that are marked on the paper when we make a graphical
adjustment, but only their differences from values found by a preceding interpolation.
we must allow |
mean errors. It
the
surpass
115
the
said
based
is
interpolation
on
number
minimum number
a
it
is
and
of observed data;
after the
new
adjustment.
If
the results
also
the interpolated
values.
to
ought
values
being
table of exclusively
When we
It
by comparison
measured values
will
diiferences.
may
checked
however, and
it
unknown elements
of the
like the
must not be
problem, according to
number,
the rules of
exact mathematics.
their weights,
will not
advantage.
It is
not necessary here to suffer any loss of exactness, as by the other normal
put
in the
it
we
like,
As
to the criticism,
nevertheless,
to
But,
if
we can
state the
mean
the rule
V-'(o_m)2
I'And
same drawing, we
m,
particularly
to
summary
criticism,
we
are able,
according to
m.
on systematical deviations, the graphical
116
From
the
this reason,
empirical laws.
such
In
of hypotheses
as
We
circumstances.
save
we have
cases
the
to
functional
much
to
work through,
and to
to check,
and
interdependency of observations
labour,
and
if
reject series
their
essential
we work by
graphical
adjustment.
Of
we
course,
ought not
it is
be taken
to
observations to adjustment.
In the pre-
into consideration,
may even
it
But
drawing of a
widely
point.
even
in
line
the form
spread,
of a
rectilinear
We
to
have already, in
number
The theory
9,
limitation.
all
the
other
its
it
ought,
occurrence in reality.
treats
especially
of
an
observation
may
possible
of an event approaches,
number
such
of trials.
observations
But there
is
whose events
no compulsion in
the
of probabilities
When
observed
every
in
to
broken
is
is
to give this
XIV.
65.
we ought
to
polygon which
then
points,
line the
is
if
In this
way
its
But,
on
the
other
and
as such a formal
indication.
If
117
then we identify
sums
of
events.
with
the
"Yes"-event,
explicitly.
repetitions of the
times,
favourable
Sg
=
=
=
tn
and
m-\-n
,u
0,
then
if
Sj
....
m
m
of only
errors,
m times "No"
against
m+M
3m
jo
this,
3m
-f
Sr
/ig
m.
we
+ (w
-j-
(121)
) /4
find then
m
Ml
mn
fit
{m -{- nf
mn {n tn)
Fa
f^i
Compare
equal to
interchanging
half-invariants
In
The
fi^.
and
order
event becomes
(m-f-w)*
are integral
functions
qj- = fXi;
1
to
represent
q.
^
is
by
and those
= ^-
= ^p =
^-^
==
m-{-n
{m-\-nY
mn {n^ 4mn + *)
All the
itself
(122)
The
and n increase
h =
we
is
represented by
= miip)
K = P<l{<f '^M+ V\
(123)
-^3
itself.
118
We
must now
first
notice here
simple
that
complete
When
(the frequency).
half-invariant
every
is
own
its
and
fixed
we have
properly so called,
thereby given as
In such cases
it
is
The theory
of probability
its
thereby gets
much more
province determined in a
of the
particularly, the notion
mean
error.
Even where the probability can replace all the half-invariants, we shall require all
the various sides of the notions which are distinctly expressed in the half-invariants. Now
we have
is
to
elicit
which
is
the
definite
particularly emphasised
to
what
rely
mean
the
in
error.
is
value,
now
Finally,
we
shall see
the point
Otherwise,
we should
constantly be
tempted
is
which
of uncertainty
degree
mean
far
beyond
the probabilities are far from typical, but that they have rather a type of their own, which
must sometimes be
All this
as a
means
we
especially emphasised.
shall be able to do here,
66.
In particular,
presumptive
errors
the frequency
for
is
repeated
of one
trial,
times,
trial follows
known.
The equations
and as the
of the events of a
is
the
sum
trial,
the
>l,
(m)
A^im)
A,{m)
Xi(m)
=
^
=
=
Np
Npq
Npq(q-p)
Npq{q^
=
=
Np{l-p)
Np{l-p){l-2p)
ipq->rp^}
Np{l-p)(l-{3 + VS)p){l-{S-VS)p).
(124)
119
The
mean frequency to
small the mean error
ratio of the
When ^
is
frequency; and
VNq. When
if
is
nearly
1,
the probability, p,
The law
of error
is
the
number
differs
the
of trials
from
little
mean
the
^Np
square root
the
of
mean
nearly equal to
is
is
mean
the
i,
p between
and
1,
so that the deviation from the typical form must, on the whole, be small.
however, we
If,
consider the relative magnitude of the higher half-invariants as compared with the powers
of the
mean
error
>l3(m).(>(,(m))-l
= -^^
VNpq
and
(125)
the occurence of
in the
Npq
great numbers of
here as always,
repetitions,
but also that, in contrast to this, the law of error in the cases of certainty and impossibility,
when
high degree,
and
while
remarkable property
jp
at
is
still
mean
will
error
0,
1.
be about
rare
in
be
the
case
under
V\-
Errors
degree.
ct.
mean
becomes
beyond
error.
infinitely
This
0.
either very
is
though
The law
of
mean frequency
the
The
99iV
hey
error
is
must be
fully
it
must
will not be
counter-balanced
consequently skew
is,
in
ct.
cannot
and frequencies of 97 or 96
in typical cases,
consideration,
errors
mean
by
perceptible
XV.
67.
of probability teaches us
how
to
to
determine probabilities
be given.
Of
course, there
are no mathematical rules specially applicable to computations that deal with probabilities,
probabilities
which do not
But
fall
120
not only
of probabilities,
life,
to
lead
us
a probability as
to
in the
but to
statistics,
be
will
it
the
to
its
errors.
conditions of
all
of probabilities rests
on two theorems, one concerning the addition of probabilities, the other concerning their
multiplication.
I.
the addition
of probabilities can,
as
all
probabilities
are positive numbers, be deduced from the usual definition of addition as a putting together:
if
sum
of probabilities
is
be a probability
to
a quality in
the sura
common,
to
mark
trial.
An "either or"
if either
whose probability
is
is,
to the
same
of the
trial
trial,
their
equally
is
are
probability of each
we
If
repeated
1,
= p.
If
= p,
being
n events
then
the
of the
aggregate
the
is
of unity.
trial
be
probability
of
as
all
proba-
in
JO
numbers of
infinite
i?,
is
a relative frequency,
it
must
relate to a trial
succeeded as conditional
please, the
trials,
we
shall
= P1P2'
N times,
is
if
As
Now
trials
The
the
if
repeated
in the multiplication
number
T, and
for probabilities.
Tj which,
frequency, takes the place of multiplier, then the corresponding trial Tj,
we
same
commence by proving
If,
np.
multiplier
Pi-\-Pi,
II.
bilities
the
probable,
If
be the probability
we have p-\-q^\,
these events
sum must
gramma-
is
are favourable.
is
probability
blance
If
is
must occur,
to its particular
t(f
tions,
These events must mutually exclude one another, but must at the same time have
events.
tical
we must
itself,
T,^
total
Np^
P'=PiPi,
number
of
121
The probability p ^PiP-i-, as the product of the probabilities p^ and p^, relates to
compound trial, which is favourable only if both conditional trials, 1\ and
the event of a
on
probability,
the factors
condition
be
may
we
proposition
the
compound
shall
in
of success
it
is
To
trials
without
trials
4-^4-^-1-/?
-^2
any
the
to
regard
other,
*^^ frequencies or
only
or
by
as
multiplicands
= Pj
|)
= P1P2,
"~T~
mark
the
is
a:h
unless
T^
if
we
trial is
if
i.
e.
compound
and
Pj
or
there
if
impossible,
P2
both p^
and p^
Example
1.
-r
P, and
But
favourable events.
P, and P^
is
found by
are
in
applicable
P^
but not
This proportionality
T^.
^^
= PiPz-
for
we
0,
trials that
The condition
that
see
the
compound
of certainty (probability
must be proper
probability,
indicated by probability
is
trial is certainty
2^2 as probabilities
"J^
is
impossibility
But
c:d.
Since
compound
get
of their
is
of freedom,
therefore
according to
we
probabilities
events, necessary
two
is
probability
trial.
if
nevertheless,
the
as
to
trial
in
correctly to be found
first
is
all
fractions, Pip.^ =p =
1) in
be possible only
1 will
when
1.
When
the
favourable
events
of
the
all
conditional
trials,
in
number, have the same probability p, the compound event, which depends on the success
of
J
all
for
If
is
the probability of
"red" and \ for "black", the probability of 10 drawings all giving red will be 7^24.
lities of
Example 2. Suppose a pack of 52 cards to be so well shuffled that the probabired and black may constantly be proportional to the remainder in the stock, then
_2625242322212019
"~
18
17_
~
52'5r50*49"48'47"46*45'44'43
the
/9n(-c)
!gg Ijg
|^
|16 |10
^^^(K))
/352(10)
_
~
_19_ _
~ J__
56588
2978'
122
after
we suppose
n years
will be
-Pr.
The
that the
(1 5a)(l
die before
(I q+-i).
2a+l)
years will be
Qm
qa+n
-f" (1
or
The required
probability of death
the
men from
After this
answer
a large
2,
player,
in
We
4.
Example
certain
-t^ )
is
will
not, as
we
+ n
years, is
here supposed,
i,
population who
gets
be a
only
reach the
will
age
case of the
special
Z,
of
of
i.
general
of the 5
then
who
It
directly.
We
2,
3, 4,
5,
6, 7,
9,
8,
k^ player
in succession will be
9,
it
is
probability,
11?
is
it
is
first
then
we
require.
present themselves
as
quite
easily
we take the
attack
the problem
more
seriously,
and examine
For 5 players we
the probability,
each of the
1,
loses
is
In such cases
such results
r*,
what
will
is
what
gets
Lastly,
of cards arranged in
game
others?
Secondly,
first
'a+fi+m
What
'a+n
/^
imagine
order,
sum
according as the
any
(^
use,
statements of mortality
for
q^
years,
= -j^
q.
after
Pn Pn+m-
PQm
consequently
the
is i will
Qm
probability
q. is
the probability
of
that
same
may
if
be interpreted as pro-
123
^^iP2 Ps)
+ ^(lU Pi)
PO Ih-
-i-
68.
the
theory of probabilities,
and
may
trial
be indicated by colours,
The
probability that
we
x white, y
and of red
black,
r.
and z red
w" -P
The number
r'.
is
the trinomial
coefficient
^
nx,y,z)
which
And
is
this
1-2-3...
+ y + g)
i.2...x-l-2...y\-2...z'
in
the
development of
(m;
+ 6 + r)
(^+J'+^).
same term
r {x, y, z)
is
(a;
white
iV
-hy -r'
times,
(126)
black y times,
{x-{'y-\-z) repetitions.
When
the
that w-\-h-\-r-\-
1,
is
imagine
(w-\-h-{-r-\- ...)" developed by the polynomial theorem, and the single terms of
the development will then give us the probabilities of the different possible events of the
repetitions without regard to the order of succession.
Example
1.
10
there are the three possible events of white, black, and red, even
numbers
and
we must
if
b,
indices,
trials in
which
and z of
x, y,
r, respectively,
and we thus
then
find:
The
probability,
consequently,
is
trial,
(i.
2,
little greater,
is
very small.
e.
probability
unless
a for and
who
gets
124
the greatest
of "heads".
If
as often as
If
=
qi
number
win?
for
and
i^
|, for Paul's
is
^2
is
the
probability
for Peter of
Paul of
for
drawn game of
for a
^^,
^.
o
1
As
are
probabilities
distributed
the
in
What
3.
Example
game which
won once
is
out of four
is
times,
repeated 10 times.
is
551124
1048576
69.
which
we
inquire in a general
is
Often
it
is
way concerning a
problem into such a one of a more general character, where the unknown
Pn of
the
probabilities,
suffixes
being
the
arbitrary value
this
theory of probabilities,
method almost
p)
0,
table.
And
particularly such
with dilference-equations.
e.
i.
a whole table
Integration of
finite difference-equations is
of the
of n,
is
arguments of the
probability,
that
that
by
known
cases, especially
equations
that,
with
functions,
we can
in
coefficients.
As
to these,
it
is
only
when
CmPn+m
the solution
is
given by
Pn
+ c^Pn =
=
k,r",
-^
(w being arbitrary),
-\-
KK
(127)
125
where
Cmr'"-\- ...
=0,
Co
rational
functions
integral
the integration
leads to,
of
I,
if
the
it
of the
many
those in
particularly
times.
shall
to
it
The
late Professor L.
of transformation, which
Oppermann,
communicated
to
me
method
in April 1871,
of numbers
Uq^
...
Ufi
*^0
"o
**!
^2
^3
~\~
2u 2
Wo
w,
=
=
2'
may
-f-
(128)
{iY2:jip{z)up,
be taken from
compute the
m's
to
M4
4m,
^"'i
6M4 +
4M4
U3
u, +
3M3
-f-
UK
W,
-\-
3o
"""3
oo
to
+00,
provided that Up
when
p^n.
Wq ==
u^
M3
=
=
M,
U-r
expressed
in
as
in (17)
single
~\~
~{'
4<>4
=
=
M2
Here,
+ '^ ^3 ^^4 +
Wi 2^2 3MJ3
+ 3^3 6^4
tv^ 4to^
-|-
*<'2
-j-
(129)
w. 4ilYl"f3r(x)Wr.
and
(18), the
equation,
z.
From
w,-
can be
(129)
we
get identically
If
we here put
=
e'
e",
then
e'
1-
=--
e'
an equation of
126
If M, is the
frequency or probability of
'
illustrate
In particular we have
!^\
^ ^i(^o+^i)
Ws
'iPo(M'o
'^
now Mo,Mi,
If
then
probabilities,
^''o'
and
equation
of their
pretty
often
we know
if
Oppermann's transformation
this
Wi( Wo4-Oi)(m?o4-2m> J
But
it
we have
the
reverse
process to find
w,-
If
(for
expresses
itself,
the
series
are
pretty simple
if
is
but they are often less favourable for numerical computation, as they frequently
simple;
give
to
problems of
by symmetrical functions,
in
to deal
easier
through a difference-
only to a difference-equation
course leads
of
suffix.
is
If
which depend
equation,
+ M',)
Wo'
M'o
for
1-2
'
on
taiten as
unknown
the
as a difference between
it
much
There
larger quantities.
a means
exists
examination of the
question here.
Example
1.
throw a
what
wth throw,
what
is
is
my
die,
and go on throwing
"two" or "three".
probability of
If the
winning?
If
till
either
game is to
number
the
is
unlimited,
Four results are to be distinguished from one another. At any throw, say the ^*,
Let the
the game can in general be won, lost, half won (by only one "one"), or drawn.
probability of the i^^ throw resulting in a win be p., of the
in half
win
Thus the
s,,
s^,_j -j-r,._j.
It is easy
to
express p.,
is
g.,
r,-,
then pi
^0,
same resulting
in a loss be q.,
gi
g,
^,
Si
and r, == a.
* throw
and
s,.
in terms
of r._,
and
s._^,
and
also
127
Pi-fi
!?,_i'
^^^
''i-i'
and
*,-i
etc.
s^_^,
diifereuce-
When we
the
or
replace
g'
or s or r by
common form
a;,
which
x,_,
integrated as
is
Xi
for
ri
+ 6J)2-';
-ir,_,.
When, by the
we
(a
=0,
-\-{Xi^2
x the
constants,
get
Pi-
3.
'
.= 42-,
and
r,
We
probabilities of
In
If
successive
game
games
are
where
of dice,
won,
ra
the
1. (2-l)_n
w
3(2-l)
game
2.
=^i -j-
probability
it
what
is
the
5in for
and we get
Poc___l
+ (?oo
9;
^^^
of
= 9't+
P<
winning
is
is
and ^n
-|-p
or losing throw,
P+<?
Example
2-'.
the
What
is
In
10000 throws?
It will
got in the
first
r repetitions.
q^=
The difference-equation
^>^,
for this is
or
^'C,
where
How?).
where
is
(b)
Ci,
2,^
the
first
integral
of
(a).
(As well as
(a)
we can
directly demonstrate
(b)
(b).
Hence
of
128
==
""'
^' Vm
1m-i
the
n*
of
equation
degree, which
Q'o
?!
only a
than 1;
less
little
The
vi.
small
done, and
be
this
unknown
values of the
enables us to get
(b)
of these
q^_^_^
ffi""
(c)
(for small
roots
or large m's)
ra's
when
in
is
even;
will
be
it is
problem
most important
illustrate a
will
(c).
We may
artifice.
to
to
means
in terms of
q^^J^^
function by
"+'
roots of an irreducible
*'0
Pi
also small.
This can
/>"
largest
aiid
got from
is
/>"+'
by dividing out
"''
of those
Then we
q.
q^,
q^_^_^,
either
by again ap-
evident that the table of the numerical values of the function which
we can
form in this way, cannot easily become of any great extent or give us exact information
as
to
the form
of the
our
example
is
But we
function.
known
we may be
(as here),
the
and,
when the
general
computations
above
described
the
until
numerical case
q^
1-004078
made
be
as
(0-9998928)'-
qmoo = 0-6577.
white and a n black
probability
ones
m^(/)
that
the
numbers
white
and
it,
this process
balls in the
balls
will
have
"^(i')
^^"^(2/-l)+^-'*'+i(y-l)
and
Ux(0)
By Oppermann's transformation we
-co
to
a:
except Ma(0)
1.
find
.(/)
taken from
0,
-{-cc
=
,
( l)''2'jff^(2;)-<T(2/),
or
is
be
x and
ball
is
repeated y
then
n x.
We
I'
of
in
ones.
In the
the
Find
black
129
The
x under
limits of
infinite,
being
^'
is
the variable,
As we have,
easily be integrated.
further,
set
By Oppermann's
inverse transformation
we
find
= (-i)"^^/?.!^)
a;= oo toa; = -f-<- This
My) =
My)
2"
may
taken from
now:
(-1)'
^a{z)
(-^)'',
expression
M^)i{-iY+'^-^a-r(z-x).(^-^y
has the above mentioned practical short-comings, which are sensible particularly
if ,
x,
y are large numbers; in these cases an artifice like that used by Laplace (problem 17)
becomes necessary. But our exact solution has a simple interpretation. The sum that mulor
tiplies /?
(x)mux{y),
of the values
all
is
the
(^)', ("^^^^f,
easy,
solve
to
analogous
If
this
to that
(axy^
problem
We
f^=^)', (")',
and
that
it
is
and
square of the
is
formed by
possible,
if
not
of errors as
found by a table
is
we make use
("-)
we
mean value
of
for
the
after
same law
y drawings
XAy)-a{^'^J
for the
-"
XVI.
mean
error
(("')'-(~T)+K("^)'-("i-')")-
70.
The computations
of probabilities with
babilities to be given,
common
in
the
we always assume one or several proand then deduce from them the required ones. If now we ask, how
that
17
130
we
obtain
it
Without experience
it
is
agreement with
is
we cannot
must be
first
and without
reality,
distinguish
sight
between two
to be purely theoretical,
inequality, or ratio of the probabilities of the several events, and in this process
or
at
mode
rate their
any
clear
as purely empirical.
is
71.
it
reason to
special
impossible to insure
means
other
tliat
to
evident
is
those
of operation,
to be
we always
more
or less
known.
On
we have the
in
typical cases
them
is
possible,
to be equally probable
For instance
What is the probability of
though certainly with the upmost uncertainty.
seeing, in the course'^or|time, the back of the moon? Shall we say | or .? 9?t: j/.
:
On
in
we have the
cases
causes
at
work
for
that,
equally typical,
know
so
much
and
-g
each of those which will produce one event, we can point out
result at
In this case
and
pr respectively,
we must
to
the
if
But even
if
such a theory
way obtain
probabilities,
errors, that
we may
may
be used
as
which are
very well
is
so
nearly
make use
of them,
We
kinds of computations.
are
infinitely small
mean
is
other
almost an established
fact is .that it
For
it
way
that,
is
game
that
babilities possible.
must be
laid
down
in
such a
all
the rules
make a
in
a game,
e.
g.
^^'^''^
131
of cards, ought therefore to exclude all circumstances that
causes
But
in
train,
judgment
become a
When
The
struggle.
we speak
of a subjective probability.
understand
that
there
who know
those
make
depend on the
it
game and
fair
The
fear
all,
to set
(corriger la fortune).
make
is
but a
little,
all
than for
the
uncertainty in
great
is
it
is
life.
that they
greater for
to judge.
Koulette
may
of a
and the
circle
whose center
in
is
The pointer
the pivot.
result of the
it
stops.
3) the
manner
in
which the
be
may
is
made
to revolve quickly,
is
game
won.
1)
and the
and
in
is
tra-
circle is divided.
unknown,
is
friction,
regarded as given,
as
especially
when we take
already mentioned,
is
very slight.
So
much
function of this length, be expressed by a functional law of errors of a nearly typical form.
maximum
one
full
many
by
If
far as 0,
revolutions
now,
for instance, it
and with
at
the arc traversed was greater or smaller than a certain value, the apparatus would be in-
expedient,
it
winning space
repeated
of the
regularly
priori
estimate.
will
be
even
exact.
very
pP, qQ'
....
sum
with
But
if
the
for
probabilities
is
of
first
approximation be
multiplied
by
the
17*
finite,
132
interval
^ qr =^
the total
imation,
...
is
for
pq
That the
initial
is
x -\- x* -^
1 -\-
we speak
is
this
x^
approx-
x^^
-\-
of
-\-
of the roulette is
position
if
is
winning
essentially
~.
change
This uncertainty
If
we may assume
that the pointer will as probably start from any point in the circle as from any other, this
determination
known
The
the
will even
third
essential
The a
priori
circle
whose mean
error
different values,
to the
essential to
is
it
determination of probability
most
^;^'
circumstance,
or a counting
of the
ratio
measurement
up
be exact, without
function of frequency.
can thus,
but demands a
a priori,
know.
according to
circumstances,
such exact probabilities as agree with the suppositions in 65 seqq., and permit the
probability to replace
method cannot
give,
is
quantitative
that
itself.
statement
Only when
we cannot
necessary, and in
measure, we must
order
the
of
bilities in
great caution
it
is
uncertainty which
evident,
as
in
priori
aiTects
the
the example of
If in the
life,
an estimate
of the uncertainty.
PJven
the dice
may
72.
large numbers,
false,
By
inferring
Owing
for every
we
of
the probability.
We
and n
event,
for
unfavourable
not superfluous;
may
of presumptive errors in
is
mean
the probability
= -^.
(130)
133
'^
a single
trial is
'
mean
rs
is,
we
are to
If
m A^
we have made,
mean
we then ask
the
for
The
mean
whether this
is
one of
still
make, and
for
which
to
mean
=-
^^ 7.
'
,t
6*
*'^^
^''O'"
i> (1
(i32\'
1)
error.
mn
(m -{- n)^ (m
or
Pi
shows that the mean error at a single
m -j-
repetitions, can be
identity
nm
The a
approximation
is
is
-\-
probability.
trial,
-\-
n)
(m
-f~
1)
(133)
^2
when the
probability
determined a poste-
is
in
two mutually
error.
therefore
be regarded as insignificant,
it
is
may
we employ
is
so
we can immediately
the law
for
of
free
is
mean
may
{m
1)
nm
+ ^2 iP) =
posteriori determination
to the
p>q (123),
which a^ (p)
errors.
trial,
- P)
_
m^n\
(w 4- n)2 (m +
,,,x
{m-\-ti)^
which Xo
m~\-n,
\)
which we are
'<^
^ "'^
for
is
by
or is a repetition
n repetitions, we have
riori
toi
those which
deviation
(m-\-n){m-\-n
which
mean
of the
is
necessary.
It
we make use
of
takes part in
must be
it,
repetitions,
but
in
is
the
seems
same way
as
the
future
to be purely
that
trials
all
the
whose
results
this
compel
statistics
probabilities, to
many
alterations
134
and hypotheses, and
of their theories
to the division
11
is
found,
15
= ~q--q'i^
=
~^.
consequently
now we
If
still
mean
Ideally,
and
mean
all
far,
i;
"
that
we
mean
by the
shall
right.
errors
are
6 throws,
...,
(1
the
mean
is
= +
square should be
the
limits indicated
(1
its
:^
'^^"
however,
trial,
]-.
the probability
as by
probability is
error?
or
seek
^^^
900'
be
to
consequently,
On
so
error oi
I's,
(1
i*) (1
consequent error in
(1
p)^
/')*)
p) -
p{l
But
---
-5-
will be
the
now
is
the
if
6(1 pf dp;
^
if
h = (l-pf{l-{l-pf) + ^&{\-pY''-p(l-p)-^
In every single
an accurate
game
die,
but
mean
This
may
mean
of
winning 72
-^
the
there
is
With
the
== 24 games.
first
terra
in
if
we
In
the
the
number
above approximate
much
caution
much chance
not
that
as to call for so
game
fractions
of
of repetiof
making
there will
be
above
X^
must be multiplied by
72, but
The mean
=
=
+ 3^-^.5184
16 + 33 = 49,
72
|-.
4,
if
the
die
had been
quite trustworthy.
73.
which
is
We
to that of
It
presumptive
errors,
produces what we may call the paradox of unanimity: if all the repetitions
probability
we have made agree in giving the same event, the probability deduced from this, a posteit
riori,
mean
error
135
nations (as well as the higher half-invariants) becomes
to
certainty or to impossibility,
= 0.
Must we
because a smaller or
only
number
greater
of
repetitions
if
Such a law of
n
fin-fjtl
CO.
we
look
more
law of errors
skew
is
^=
(i^
must be
mean
is
error,
so small that
it
may
the
0,
that,
number
Add
must be
it
explained,
follows
that
it.
//^
must indicate
that
of a
is
must warn us
it
it
is
number,
0,
it
indeterminate.
But
0.
the ratio
to this
the square
because
itself
as here,
0,
in
Oj /13
errors, to
closely at the
of
to be cautious
computations with such probabilities as observed values, where the computation, as the
method
for
as
unsuitable
material
of
all
Another thing
observation.
computation,
if
it
is
does not
we must
that
explain
the
also
reject
unanimity.
As an
c. 20'''
c.
60"^
the
The
in the
computation of the sought constants of the formula, but the formula can be employed only
when
it
towards
it
approaches asymptotically
The paradox
that
It
-J^Jl1_
(134)
(Bayes's Rule)
P
The
proofs
In the "Tidsskrift
for
tried
m
m -\- n
readers
who take an
that
have been
made
to
136
Bayes's rule has not been employed in practice to any
not in
statistics,
though
it
a convenient way,
in
formula
of a
we
rule
particularly
as
we
as,
the
determination of
after all,
certainly
the
give
mean
of the
But
and
up altogether.
will
m -j- n
events out of
for
for
the rule
it
give
greater extent,
this science
error
The
true
from
be
to
result of such
probability,
the
can
of the
result
In order to
we assume
we have now
and H unfavourable events, then the probability, being looked upon as the
//
favourable,
favourable
mean
value,
is
determined by
m -j- w
of which Bayes's formula
is
much
-|- /i -|-
if
we knew
to
= =
v
1.
Bayes's rule
as
(w
^^
and
for the
If
in-\-n
It
-\-
^2 {on
-j-
-\-
computed
this
value, that
(fin
{m
(w -f w)
-\- fi) [n
w)
(m
(n
is,
mean
-\-
(m -^n)
the square
between
m)^
I/)
fi)
-\- v)
trials is
(w -\-n)pY
^2
{m
(m
case
v)
-\- [I -\-
'
1)
deviation
and {m-\-n)p, we
(m -|- w)
now
k^.
of the
find
[i
appears at once from the latter formula that the greatest imaginable value of the ratio
With
maximum
of
it
will
v.
In Bayes's rule
/^
and
{i
= =
postulated
be seen that
we
proposition
is
1.
Here, therefore,
to that of the
mean
hereby demonstrated.
if
is
1 is
error.
But
at
there
is
137
only an a priori determination, however
we take the a
priori probabilities
ra
of the
uncertain,
for,
and
(1
we
probability
s) against, instead of
are
seeking.
and
fi
m^
(137)
much
so
deviating
the
as
mean
from
error
If
so that
v,
the
it
observation
the
in
posteriori
determination.
we can always
Neither Bayes's rule nor this latter one can be of any great use; but
mean
Where
value
have
may
the
said,
be used in
definitive
all
cases,
results.
if
we
On
interpret
have to be rejected on
account
XVII.
74.
of probability
result
game
it
is
of the
entails
stake.
each of them
is
V,
mathematical expectation.
of the
has a value
The question
and
is
the
How
chance
of
winning
we
to
compare
are
Imagine the
clear,
a computation
latter
to be repeated,
we can speak
won through
is
is
MEAN ERROR.
ITS
probability,
that the
sum
of
probability.
large, then
The gain
if
to "be
expected from every single game is consequently pV, and this product of the probability
and the value of the prize is what we call mathematical expectation.
The
pV
which
on the quantity of good things which form the prize, but also on purely subjective circumstances,
sort of
among
others on
good things.
called the
An
how much
regarded as a failure.
For
it
is
is
138
the
but
property,
player's
it
We
subordinate circumstances.
at the
of the
of that
It is evident,
unbound games
several
games.
mathematical expectation
total
The same
the
is
we
if
case,
play a
Example
a
nothing;
expectation
We
1.
play several
sum
equal to the
is
in
game
this
which each
we
case
latter
of partial ones.
s.,
ixO + Jx2-|--Jx8^2s. A
then
we
throw of 4 or 5 wins 2
is
made up
In
if
The
s.
stake
of 2
total
mathematical
will
consequently
s.
We
1)
In computations
2.
Example
number
of persons
his
the
at
dying
of the various
exact
is
living
1(a)
ii-.
may
at a given
The
a.
age
kinds
dx,
and
The value
now a
an endowment of
of
years old
is
then
see, is
most
Such
is
now a
of an
years old
the formula
a:
where /(()
But
it
from
these
all
V, payable in
(1
(1-j-yo)-')
who
^'
^^^^^^
J)(a)
easily
l{z){l+p)-'.
The value
person
capital,
l{a)(\+p)-
D{z)
a table
j,
is
^^+Pf
l{a)
which, as we
alive,
'
is
years
of
probability
annuity,
shall
live,
v,
due
at
the end
can be computed as a
x
00
and Z)(qo)
of
every
sum
year
of such payments,
or
by
00
0.
deserves to be mentioned
game whose
first
through which
in
the
is
most
year being
'
T/I""^^^
'
'"
139
the second
,
I
and
so
on
(a)
we
In this way
expression
X
find
for
00
x
-^S^{lia + x)-lia + + l)){l-il+p)--).
l(a-\-x-\-l)) =
00
sum ^(l(a-\-x)
Since the
may be
7- J
and
this
we
1(a),
(140)
written
^)2^i^+-)-Hu+x+i))ii+pr
X
of
the
is
is
of
sum
payable at the
expressed in
mean
it
error
for,
owing
often
skew.
If
much
the
value
V is given
=fV,
mathematical expectation, tl
free
is,
X^iH')
total expectation of
By
free
safely
The mean
error
is
or
=^
computed by
(141)
p{l-p)NV^;
(142)
H" = EpiNiVt,
we have
Ipi{].-pi)NiVi\
(143)
highly
we
are
to
uncertain claims
or
to
enter
outstanding
balance of accounts.
the person
the
= pNV
how
error of
get
X^(H")
mean
=^(l-p)F.
E'
for the
same game we
iV repetitions of the
and
and
in
/i,(/^)
If there are
and combinations
that the isolated laws of errors, here as for the probabilities, are
140
stances be contented with
mean
and
error,
it
by 4
a passionate
if
player would venture a stake which exceeded the mathematical expectation by the quadruple
mean
of its
On
error.
mean
error
A game
1.
Example
is
but
is
^, the
then (0-8
is
prize
+ 2'41/w)
He must
(J*.
much
has got so
2304 games,
460 g 80
enter
will
w games
fi.
game
only
or
capital
also so
become very
many
safe;
to
regard
part
of
game,
ij^
mean
error
game
of taking
in
part
(1-0
144(0-8
the
0-4)) ^.
who must
for
But
man owns
every
way
mean
error
cts.
cts.
per
x 48.
which
after all,
game
is
But who
not worse
is
is
the
(a
40
will
however, he
If,
and
customers, that
or exactly
cts.,
as
credit,
prudent
if
x 144 + 2'4 x 12
will
only augment
No prudent man will enter upon such a game, unless he can thereby
in this way we insure our risks, because it is too dangerous to be
If the
the mathematical
If the
fix
consequently
In
Jf.
stand
thus
expect 144 games to be played before the prizes are to be paid, he cannot without
may
= 144
is
that
we pay 40
rather a
{-^2-AViM
cautious
as above)
the disproportion.
own
"one's
insurer".
cts. for
the excitement
person
may
being only 28
if
also con-
80
cts.
or
For a poor fellow, who has only one dollar in his pocket, but
some reason
necessarily get 8
only 2304
and
fi,
Jf,
fails
if
would be exceedingly foolhardy if he played 2304 times or more in that bank. If we must
run the risk, we can do no better than venturing everything on one card; if we distribute
our chances over n repetitions, then we must, beyond the mathematical expectation, hope
for
Vn
Example
total
insurance
2.
of
Two
mean
f 10,000,000.
error
The
yearly
probability
of
damage by
Both have
to rest satisfied
How
high must
pany
premium, when
there
has insured:
is
sufficient
deficit in
fire
is
for
^,
and
guaranty-fund
each
fiscal year.
com-
141
142
we may
their differences,
even
the computation
in
mean
expectation from
errors reduce to
all
it
to the losses.
X^ (N,H(l,
il-p,),
...
w))
N{p, {a,-
Ha,
can
now compute
mean
the
))+
+^(a_//(l,
(146)
n)y-).
errors
in
the
examples
and
2,
in
In
74.
we have
-i(0)2
+ i(2) + ^(8)2_2^ =
we now
sum
of a
number
of
endowments;
for
we
from the rule of unbound games only in the absence of the factors
differs
i,(H)
the
{l-p).
We
No.
=^Qg
+ ^)-H(^ + ^+i))a-a+p)-')y
^^iJJa)2{^(^(''
77.
mean
errors
free
of mathematical
from
(147)
a priori by good theory or found a posteriori from very large numbers of repetitions.
determination
is
observed
numbers of
trials,
or if probabilities
may
may depend on
must
or not,
total ^2-
of the
As
mean
for
errors,
error,
depend on
in
the relative
Whether some
to the theory of probability it is characteristic only that the parts of the squares
research
This
values
we
expectations
error,
its
next discovery,
least
we have
squares,
to
then,
compute
in
the
When
order
mean
the
restrict
errors
of its
the limits
is
of
co-ordinates
143
at the next opposition. Ordinarily these
mean
may be wholly omitted, though this yij is analogous to those from 75 and
But when we have computed a table of mortality by the method of the least squares,
we can certainly find by that method the mean error Vki {P) of the probability of
observations
76.
computed from the table; but if we are to predict anything as to the uncertainty
with regard to n lives, and with regard to the corresponding mathematical expectation npa,
then we must not, unless n is very great, take the mean error as naVX^ip), but we
life
must, as a rule,
first
a]/np{\p)-\-n^/ii{p).
take
^2
(^)
'i^
consideration,
-"C>*xK(c>"
Fig.l
Fig.2
Fi3.3.
'_^-"-^'^-'^Z'\,ISltiL
14 DAY USE
RETURN TO DESK FROM WHICH BORJROWED
LOAN
DEPT.
HECDLD
MAY
U. C.
JUN
2 1999
BERKELEY
IJ)21A-20m-3,'73
(Q8677sl0)476-A-31
R)UC.-KYCH. LIBRAW
General Library
University of Califortiia
Berkeley
LD
21-100m-8,'34
s#'"
*^f#3ifflf#feAvA'
.'/^'^%^
^'J^-KSCSSriv,
I'^.TT^^*^ >V>'T
.V
;e^,:
l3S^-:?c^^