Beruflich Dokumente
Kultur Dokumente
ill
11 I
"111
Vbr
:..:
Hi
mill
iiiiiijiii
I-
BRAR^
'>i
in
University of California.
<
VI
OK
Class
ON THE
COMBINATION OF OBSERVATIONS.
ON THE
THEORY
OF
ERRORS OF OBSERVATIONS
AND THE
COMBINATION OF OBSERVATIONS.
SECOND
'
EDITION, REVISED.
Hon&on
aIACMILLAN AND
1875.
[All Eights
reserved.]
CO.
K.C.B.
QA
Camfcrt'trge
PRINTED BY
C. J.
CLAY.
MA
of Probabilities
is
One of these
relates to those
nomical observation.
Tt may be difficult to commence the investigations
proper for the second division of the theory without
referring to principles derived from the first. Neverit is certain that, when the elements of the
second division of the theory are established, all reference to the first division is laid aside and the original
connexion is, by the great majority of persons who use
theless,
The two
persons
and
divi-
those
practically they
become two
different
sciences.
and observers
in
have thought
PREFACE.
VI
it
desirable to
draw up
have
done
in a General
Xo
Theory of Probabilities.
ployed.
G. B.
AIRY.
G. B.
February
20,
1875.
AIRY.
INDEX.
PART
I.
Section
1.
Article
2.
3.
....
4.
5.
Instances of Mistakes
C.
Section
i).
2.
ib.
ib.
Treatise
8.
10.
11.
12.
13.
Algebraical
of
...
ib.
form to be expected
law
combination
...
6
7
many independent
ib.
INDEX.
Vlll
PAGE
Article 15.
16.
17.
Investigation of
J
S
10
11
dt.e~&
Jo
IS.
Investigation of
f"
I
.12
'
2
.
Jo
20.
x + 8x is found to be
between x and
fall
a- 2
t- .e~c 2
.8x
.14
cJtt
.15
21.
22.
23.
result
table of values of
ib>
16
3.
Consequences of the Law of Probability or
Frequency of Errors, as applied to One System of
Measures of One Element.
Section
25.
It is
of Probability applies
"Mean Error"
26.
Investigation of
27.
Investigation of "Error of
28.
29.
Mean Square"
.
.IS
.19
.
investigation of Pro-
Jo
bable Error
30.
Remark on
the small
22
number
of errors of large
value
31.
32.
20
.21
/""'
7''
's/
23
ib.
24
INDEX.
Section
Remarks on
4.
the application
of
these processes
in particular cases.
PAGE
"With a limited
Article 33.
number
imperfectly followed
24
34.
PART
ERRORS IX
TIIE
.25
II.
Section
of
or
35.
The multiple
37.
itself a
is
simple measure
of
26
not
27
ih.
Law
Sectiox
6.
39.
The problem
is
43.
Results
that, for
the
sum
of two independent
Law
.33
INDEX.
PAGE
Article 44.
Error
33
45.
47.
Fallible
solutely independent
34
for the difference of
two
.30
all cases here to be treated, the Law of Frequency has the same form as for original obser-
In
49.
vations
Section*
37
7.
in
50.
51.
Probable Error of
52.
53.
Probable Error of
3s
R + S+T+U+&C
X +A
ib.
33
where
2 + ...4-X,
the
bable error of
55.
Section
5G.
(b.
nXi
8.
40
X X
1
i} ...X
41
42
the
Moon
43
INDEX.
XI
The
is
is,
not certainly
known
59,
60,
is
before
the divisor of
of
61,
44
the same as
ib.
sum
n 1
of squares will be
instead
45
47
FART
III.
combination ; caution in
its
application to "entangled
measures."
62.
First class of
measures
quantity which
are
direct
is invariable,
measures of a
or whose variations
known
49
63.
64.
The combination
to
be sought
is
is
the smallest
possible
ib.
65.
6G.
50
result,
of complex
51
there will
XU
INDEX.
PAGE
Article 67.
Second
measures
class of
when
the corrections to
simultaneously
this is also
....
a case of algebraical
52
11.
Combination of simple measures; meaning
of " theoretical weight;" simplicity of results for theoretical weight; allowable departure from the strict
Section
rules.
68.
69.
53
Independent measures
good
their combination-weights must be
in-
error of each
70.
54
If the reciprocal
of
(probable error)
"theoretical weight,"
their
be
called
combination-weight
oucrht
weight
to
;
sures
">.")
72.
Instance
73.
We may depart
Section
74.
12.
Instance
transits
(1).
60
of result
58
stations
75.
"><;
and
for theoretical
result
weight
(jl
INDEX.
Xlll
PAGE
Article 76.
78.
Partition
79.
Instance
is
(2).
....
ib.
Instance
(3).
.62
.04
SO.
ib.
.65
actual errors
82.
84.
The
06
difference
vations
Section
to
"
13.
several
70
unknown
minimum
squares.'"
.71
87.
88.
tions
89.
72
90.
Symbolical
error of
91.
6S
73
equations
for
x minimum
74
.
.75
INDEX.
XIV
PAGE
Article 93.
94.
.77
This form
when
minimum
properly multiplied."
Danger of using
squares."
96.
97.
term
this
78
.79
practice
Section
14.
SI
plying
99.
Instance
tions
100.
to
1.
quantities.
among
Instance
unknown
several
several transit-observers
.82
2.
triangles
101.
So
of each measure
different
for angles
must first be
between sta-
measures
ib.
102.
S6
103.
ih.
104.
These equations
SS
105.
10G.
No
will suffice
;
it
admits of
instance
neous
107.
Solution of equations
S9
ih
is
troublesome
.90
INDEX.
XV
Section
satisfy
Article 110.
Instance
1.
angles
91
111.
112.
113.
Result
114.
Instance
....
92
ib.
2.
In a series of successive azimuthal
whose sum ought to be 360, the sum
angles,
proves erroneous
find
to
94
115.
Result
116.
Instance
117.
ib.
3.
station, all
....
.
118,119,120.
122.
ib.
PART
may be
preferable
95
96
97,99,100
.101
IV.
Section
16.
may
be recognized ;
and
investigation of their
separate values.
124.
125.
is
.
not
.103
Error
ib.
INDEX.
XVI
Articlel26.
....
127.
12S.
Investigation of
129.
130.
Mean
li>4
ib.
Discordance, supposed to
its
Probable Error
Mean Discordance
105
ib.
Com-
puter
131.
PAGE
106
ib.
"We must not in general assume a value for Constant Error for each group, but must treat it
133.
134.
135.
Resulting combination-weights
136.
as a chance-error
equations of
107
.
minimum
10S
109
.
.110
CONCLUSION.
137.
inconvenience,
APPENDIX.
Practical Verification of the Theoretical
quency of Errors
Law
.114
COEKIGENDA.
Page
and
Mean Square
Page
61,
of
Sum
of Errors
7,
a + b + c + d + &e.
"final apparent results, as
insert
actual error of
read
,,
'
,,
'
,,
actual error
'
'
'
read
'
'
apparent
read
'
result
'.
'
'.
apparent
'.
OF THE
UNIVERSn
ON THE
ERRORS OF OBSERVATIONS
AND THE
COMBINATION OF OBSERVATIONS.
PART
I.
FALLIBLE MEASURES,
OBSERVATION.
1.
The
1.
Nature of
the
which
different Estimations or
Measures are
liable.
2.
into a cup,
ber.
will
incorrect.
But
if
incorrect,
more probably
it
peculiarity, that
it is
may be
to
which
There can-
3.
weight.
its
cubical content, or
any amount
(practically not
may be
in error
exceeding a certain
by
by
limit),
nute.
It is to the
Errors.
may
be called Graduated
If,
Sand-Grains
so small that
is
may be
by whole sand-grains
fractions of a sand-grain.
In this
practically
5.
kind
In
case,
or
Graduated Errors.
all
is
of a simple
instance,
by
it is
desired to
know
may
dif-
for
NATURE OF THE ERRORS.
may
length
and
this
method
estimate
its
Errors.
measure
its
length by a yard-
But besides
be
this, it will
be
many
entire yards
not
there
may
is
made with
may
of the whole
a micro-
number
number
but there
of whole revolutions, or
be called Mistakes.
in-
may
is,
These Mistakes
The
errors therefore, to
vestigations apply,
may be
in-
considered as characterized by
will
A2
we
Strictly speaking,
8.
"error."
no "
and therefore
it
may happen
positively
assert
is
not per-
that there
And,
the word.
is
in
like
among
may = 0. With
certain error
may
When
still
be
the term
is
is
the
no fear of misinterpretation.
Law
2.
9.
all
is
When
to be
determined a priori, we
fraction,
whose numerator
is
number
limits,
the
is
num-
included
is
the
bability
"
limits.
to
be deter-
10.
is
indefinitely great,
First, that,
two conclusions
though there
small
is
in
is,
any given
case, a pos-
and therefore a
fall
" probability."
of a large magnitude,
sibility of errors
still it
the
may
is
and
E + he,
where
fall
is
be-
large
he being
Or,
if
it
fall
Thus,
probable that
will fall
the distance
it is less
is
it
it is
fall
will fall
11 inches.
Second, that, according to the accuracy of the methods
must be assumed
for
is
is
real error
not contemptibly
SIMPLE ERRORS OF OBSERVATION.
But
small.
ficant that
in measuring
bility that
no
man
think
will
and 11 yards
will
so insigni-
worth consideration
it
is
may
and
between 10 yards
fall
It
may,
is
mode
with this
fall
of measuring,
may
11.
braical formula
error will fall
which
is
and
+ Be
Inasmuch
(A)
interval of limits,
The term
(B)
The term
or parameter
probabilities
sure,
and
measure.
must be
is
c,
of the form
when
cf>
(e)
same
Be.
as e increases,
and
e is indefinitely large.
< (e)
which
probability in the
must diminish
<p (e)
indefinitely small
(C)
is
as,
we multiply our
must be
an
(where Be
is
If (as
seems
likely),
is
and
form
yjr
(-) x 8 (-)
or
i//-
(-J
where
will
be of the
c is small for
[The reader
recommended,
is
12.
Without enter-
ing into
we may
The fundamental
13.
is
may
many independent
causes of error
chance which
produce an
different magnitude.
not of
is
is,
error,
affects
of either sign
each of
it
inde-
and of
treated
of
Chances
then, supposing
number
to
This
is
observation.
is
most
it
Suppose then
14.
errors
may
-, -7i +
be,
l,
one source of
that, for
-?i
2,...-l,
+1,
0,
Suppose that,
may
also be,
-n,
and
on
Ti-2,
2, ...
n-1,
-ra+2, ...-1,
0,
1, 2,
...n-2, n 1,
And
suppose that
and
duce an error
The
I.
if
we
first
step
is,
series,
first series,
so on,
to ascertain
Now,
n,
is
15.
-n + 1,
so
the
error,
we watch
I.
we
by
g-(n-l) e
therefore the
~n0 V-l
g-(n-2) fl
V"l
('i-2)
V~l
(n-l)
itself,
And
V-l
),
_i_
>H
times.
WvM
-[n-l)0 V-l
\M
in the expansion of
g-1*-8)0\'-l
(-2!0
V"l
^"-1)0^-1
^0 v'-l
number uncom-
by
either
mV_1 or
,
The number
(6
e~
^" 1
Wyht or
,
same
by \
(e
of combinations required
wV-i_|_ -z0V-i\
or the
if
term independent of
as the
by
V-i
as the
_|_
16
is
^ + e' ^
1
16
).
therefore the
same
in the expansion of
-(-D
V-i _[_
term independent of
in the ex-
pansion of
cos 10 x {1
+ 2 cos + 2
0,
from
if
to
be multiplied by
will
combinations required
\"d6 cos 10 x
.
cos n0} s .
= ir,
number
of
+ 2 cos 6 + 2 cos 20
...
+ 2 cos n0}
s
,
[*
7T
c70
cos 10
jo
And
are,
ir,
we
+2
Jo
7T
or
(1
is
cos 20
the total
number
is
(2n
+ l) s
SIMPLE ERRORS OF OBSERVATION.
10
Consequently, the probability that the algebraical combination of errors, one taken from each series, will produce
the error
is
1,
[2n
+ l)*'7r
2n+l
/sin
f*
dd cos
.
19
s
2
In subsequent
steps,
large.
To
16.
which
is
assumes
2>i+l
sin
e
(2?i
(as
the exponential
+
is
1)
sin -
than
2n +
= it;
but as succeed-
ing values of the fraction are small, and are raised to the
high power
with the
s,
first
powers of
6,
they
may be
it
will
be found that
AJ{n{n+ l)s}\
where
B is
11
The
expres-
VG
+ 1)
7T V{H-('tt
'
S\
m
i,
a.cos
r-77-,^v<3 -,
_,.
l_Vi0H-l)sj
To simplify
fr+<xc.
H b
f,
V
this integral,
it is
'2
.(l+ +&C
2
be remarked that
to
e~ c
extreme rapidity as
terms
and when
in the
t is
While
increases.
small, the
is
by an excessively small
plied
Also
coefficient.
is
it
multi-
appears
(as will
this
may be
it is
The
rejected.
integral
is
number
therefore reduced
to this,
a
\/G
7r
'
As the
17.
dt
\j\n (n
e~ \
first
There
It
at cos
1) s] J
is
'
\/{n (n
\/G
'
1) s}
no process
for this
purpose so con-
which
is
12
= e" f\
Let # and
f = x* + y~.
and
section,
y
Then
may
following Yfays:
By
= 2tT.
dt.t.~ P =7T.
Jo
By
dx
dy e~^ + ^
.
oo
=(4 //- e
x (/."'^-
e-l\
=o
00
for
r^
?''
i'
what symbol
Hence,
and
dt . e~^ )
18.
ac
i =i CC'
be used
cfy
"
dt
'
= -
ir,
dt cos ri
.
e~ l \
Call
Jo
As
and
bo
r,
Thus
dt.t:sin rt.~-\
^=-f
dr
J o
= - sin rt
e~
'
jdt
from
cos rt
13
e~ fi,
to
oo
the
first
^ y. Thus we have
dy _
di-
= ~ rv y
'
way,
y=
Now when r = 0, we
C.e'i.
the value
val
of y for that case
is
---
Hence we obtain
tin ally
at
19.
we
r, we
If
respect to
cos rt .e
differentiate
this
find,
dt.f. cos rt
e~ t2
^1
'I
and expressions
never
infinite.
we
differentiate four
The right-hand
expressions are
of similar character if
This
is
we
referred
the integral.
14
20.
now
Article 18,
2yV' ij[n(n+
end of
of notation,
end of Article
we
1G,
e 4(n+l) t
l)s\
14), will
of
I,
(see Article
is
magnitude of
If
obtain
all
and
between
lie
and
the probabilities
all
?
+ l.
In order to
lie
81,
now we
we may
between
from that
above,
fjir' \/{-in
Here
Hsa
(n
+ 1)
e in(n+lj7a
s]
is
Let
= mx,
where
m is large
\/G
v%'
T
.Let
jl
/{4m
(n
l) .8
,/
"'
.
+ l).s}'
-
*"
e 4n.(+l).s
,
^ =
4n(n +
c, wliere c
may
$x
be a quantity of
magnitude comparable
to the
15
magnitudes which we
shall
we have
between x and
x+
finally
Bx,
-t
1
j-
c-
Bx.
C\fir
This function,
racters
We
it will
21.
through each
series, as is
+ or errors
also
we
And
same magnitude.
of the
For
in this case
this,
however,
22.
which
this
is
of the
it
process
will scarcely
In
errors.
gives a
c2
which,
number proportioned
between x and x
falling
puted
when
be
entirely in accord-
by
is,
multiplied by Bx,
com-
16
LAW OF PROBABILITY OF
which the abscissa represents -
ERRORS.
17
magnitude of an error
to the modulus,
magnitude.
Here
it
will
to
Magnitude of Error
= 1*7
x Modulus
and
20 x Modulus,
18
is
expected the Frequency of Error to follow; and which, without such an investigation as Laplace's,
assumed generally
and
we might have
for
general form,
For these
17 e
c y7r
'
c-
Bx,
3.
Consequences of the
mag-
x and x + Bx.
Law
of Errors, as applied
of Probability or Frequency
One System of Measures of
to
One Element.
The Law
24.
Errors,
of Probability of Errors or
to this.
being a
Suppose the
total
number
Frequency of
of Measures to be A,
may
then we
whose magnitudes
fall
expect the
between x and x
number
Bx, to
of
be
-~
i e &
Bx,
C V7T
where
c is
but different
for Different
One System
of Measures,
Systems of Measures.
It
is
partly
related to
25.
it,
This
in
modulus
c,
or other constants
may be
'
errors.
MEAN ERROR.
19
negative errors.
Article 24
and
to
may happen
to be
positive or negative.
Conceive
26.
which
to be
is
sider the
now
measured
is
known (we
it
is
The
be found.
number which
the
mean
readiest
is
Modulus
to take
is,
and
mean
take the
method
to
of observations
is
numerical
mean
JVTean Error.
It
is
is
Since the
included between
to the
Its relation
number
of errors
x and x + Sx
is
be called the
mere numerical
to be regarded as a
thus found.
may
This
of the two.
Modulus
is
whose magnitude
- x~
c2
Bx,
and the
c sjTT
sum
sum
differ sensibly
r e
*
.
fi2
'
2
.
x,
xSx and
;
c sjir
A r,a x
from
_*!
be
cA
B 2
20
The number
CtJlTjQ
Mean
is
error
positive
1
=
V 73
this,
"
Similarly,
Mean
And
negative error
therefore,
Mean
= -=cx 0o64189.
Error
V7T
And
conversely,
c
By
= Mean
of errors
27.
is
Error x 1 772454.
exhibited.
It is
(as will
ap-
The
positive
and
root of that
-**
Bx X X2
ERROR OF MEAN SQUARE.
and the sum of
The
+0
all
dx.e
--
<?
.x
+ co
Ac 2
= + -~-
i-
_*!
x.e
c2
and
oo
Square
(-Ac
i~
first
21
is
+x
of errors
and
,
the Error of
Mean
is
'1
cj^ =cxO-707107;
or c
It
28.
= Error
of
make
different
meant by
this
is
use of a
It is not
a more pro-
attached to
is
is
it,
number
the
sign
is
attached to
when
of positive
and
that,
it,
remark
value
that, as the
is-
number
dx.e
2
,
we have
only to
up
to the
of positive errors
and
as the
whole number
of
oo
positive errors
errors is
is
-_-
we must
x which makes
-f'
1 p dx.e.c
or
1
C \/7T J
For
2!).
dw.e w
equal to j.
*
V 7T Jo
this purpose,
dw
V 7r J
u2
'
It is not
all
expressible functions)
is
is
we
common
shall
VtJo
o-o
merely
to
dw.
e"
PROBABLE ERROR.
By
of
interpolation
which gives
0*476948
value of
among
for the
is
And, conversely,
x 0476948.
x, is c
we
these,
23
= Probable
Error x 2096665.
The reader
30.
table
how
value of
nearly
or
all
will
For
it
will
gral
when
multiplied by
and negative
or
w = 1*65
or
up
to
49
of the
from
error
that value of
w=
error
number of positive
number of errors up to
(the entire
Thus
it
= 1*65, we
to
w = 30, we
have obtained
up
w=
and
49999
f the
K
0nno
sign.
we may
conveniently exhibit
24
25
if
There
34.
quently that
is
it
the results of a
be found
number
of observations,
it
will frequently
of observations
are
fre-
In collecting
number
There
nitude.
is,
Yet a consideration
error.
of the law of
Frequency of Error,
as exhibited in the last Section (which recognizes the possible existence of large errors), or
a consideration of the
num-
by addition
complex
occur
of magnitude,
error), will
and
if so,
and thereby
to
produce a large
may fairly
may perhaps
may exist (as in
errors
We
we know by
come
it
is
sufficient
COMBINATION OF ERRORS.
2G
PART
ERRORS
II.
IN
MEASURES.
5.
This case
35.
portant that
ment.
we
Suppose
exceedingly simple
is
make
shall
it
but
it is
so
im-
that, in different
measures of a quantity X,
quantity
Y=nX (an
y =nx
errors of
them,
the magnitudes nx
between them.
= y,
The number
nx + nSx =y
+ By,
or of
magnitudes
of Errors in Article 24
fall
becomes
of errors of
between y and y
+ 8y, may
A
or
c%
be expected to be
_**
.
C *JlT
this
Sx,
27
the same as
is
v-
071.
nc V7r
From
this
we
future combinations,
an
original measure.
nX may
(2)
be used as
The modulus
is,
all
nX
for
(3)
of
nX will
therefore
It
Error
may be
the
quantity
Mean
the
The
of
Probable Error
36.
=n
had been
if it
Mean Square
The
X cannot in
We do not mean
Y which
equal to n X.
is
to the
ment
5,
&c, a judg-
road about 100 yards long will in no degree aid the judg-
ment
The quantity
nX
is
in fact
is
not
that
we
Another caution
must most
to be observed
carefully distinguish
between
is
this
nX the
multiple
COMBINATION OF ERRORS.
28
of
X (on the one hand), and the sum of a series of n inde+ X + &c. + X (on the other
pendent quantities X,
hand)
...
Xv X
probable error of
(Article 53).
6.
Law
Mean
sum
Fallible Measures.
38.
C of measures
of errors
whose magnitudes
r-
fall
c~.li-
C\/7T
c
errors,
And
F of
measures
of errors
X,
in
whose magnitudes
-t
e
r-.h,
errors,
And
29
Z is formed by adding
X and Y together.
It
X+
^or
of
is
39.
we
suppose that
will
Y.
all
x n x x,
,
number
for
x", for
C7-
x 2h,
x h, x + h, x+
C\Jtt
of
magnitude x
of
magnitude x
h,
2h,
and
is
so for
Thus, putting
and putting
2h,
X will be
<?
C'.e a
h;
/i
a" 2
of
magnitude
of
magnitude x +
of
magnitude x
C'.e~c .h;
3
x,
h,
C'.e e-.h;
x"-
and
it is
plain that, by
+ 2h,
graduated
Ce'^.h;
we
this state
please to that of
errors.
magnitude y+2h,
of
magnitude y
+ h,
F'.e
Y will
.h;
- vF'.e f .h;
2
be
COMBINATION OF ERRORS.
30
magnitude
of
magnitude y
h,
F'.e
of
magnitude y
2h,
F' e~
+ y = z.
Now
Let x
40.
values
possible
value of
(F
of
(0
of Z,
F'.e f-.h;
y,
v"
.
We
of
all
number
CF
the
possible
of
of combina-
result of
form
in
will
h.
in order to
The number
Article,
7-
tions.
f-.h;
we
series of
of com-
we examine
If
the
be
4/<,
z-Sh,
z-
shall therefore
Z in
z-
2h,
h,
have a
z,z
+ h,z + 2h,
series of
3h, z
-ih.
magnitudes of error
41.
Now
if
X and
we have adopted
Y.
z,
of errors
of these combina-
magnitude
h),
we
find the
following:
combining x
2h with y
2h, the
C'.e~*.hxF'.e S'.h
or
number
is
C'F'.hxe'* P.h;
combining x
li
with y
the
4- h,
number
31
is
G'F'.hxtT + 'P.h;
combining x with
number
the
y,
is
combining x
+h
h,
with y
the
number
is
C'F'.hx e~^~%.h;
combining x + 2h with y
2h, the
number
is
r
C'F' .h x e~~^~f -.h;
and
z
for y,
If
we put
and
both ways.
= z x + 2h z x u
we
when
for
XV
?/2
e~ c2
~f-
x we put
x
continued
value of
,3-2
h,
(Z-X)-
e~&~ "T*
or
h,
h,
2h,
x,
x+
h,
x+
2h,
z.
nitely small,
The sum
is
of these, supposing h
altering
made
the
indefi-
the same as
+ oo
X?
(Z-X)%
- 00
where
z is considered constant.
Introducing the
F = OF
C
~-x/
^,
yvT
7
c\>7r
77"
c 7r
factors,
COMBINATION OF ERRORS.
32
the whole
magnitude h
between
and
+ h,
CFh
r+
is
to
_*2 _^r*l2
.
&
/a
be regarded as constant.
The index
42.
7
dx
'J-
cfrr
where
be
will
of the exponential
is
easily
changed
Let
+/ = /,
2
(V +/V
ef
+f
~^=- a--q~^=
c
z*
is
:,
9'
dx = d%, and z is constant for this investigation), the whole number of errors of Z, whose magnitudes
are included between z and z + h, will be
And,
(as
CFh
cpr
But (see
+ 00
-
- X
Article 17,
_|5
+c
Jy
-?
J _oc
cf
in this case
qf
CF
33
_*?
+ h,
will
be
CF.
Comparing
43.
this expression
precisely the
same as that
for
or for
for
Z is
Y; the modulus
being g or
V(c
Hence we have
two
cally to
).
remarkable
X and Y are
result.
When
added algebrai-
Z will
for
+/
this very
determinations
fallible
X or
will
of
And
44.
modulus
for Y.
Mean
Mean
of the
Modulus, we have
(m.e.
(e.
m.
s.
ofZ) 2 =
(m.e.
ofX) 2 +
(m.
e.
of
Y) 2
of
s.
(p. e.
A.
COMBINATION OF ERRORS.
34
for
the Error of
They
constitute, in fact,
inasmuch
the reader,
"but
who
any difference
prefers
Mean
as,
using
"We
shall
most exten-
expressly noted
is
Errors,
may form
the
e." for
"p.e." throughout.
It cannot
45.
X must be absolutely
to
form
its
and the
40 and 41 depends,
tion
measure
single
measure of Y;
If
to give a
is
As an
illustra-
the earth, or
of the
same
'
stars at the
by observations
Wight
to a station in Yorkshire, is
determined by
stars in
is
determined by
35
in the
measure of
X are
Then the
the measure of Y.
of
+ Y= amplitude
to Shetland,
mination of
of
Wight
Isle of
the
theorem
(p. e.
of Z)'
(p. e.
Xf + (p.
set of star-observations
made
Y (by comparison
and
of Y)*
determine
e.
applies strictly.
tions)
of
Isle of
Wight observa-
of X, based
upon a
star-observa-
Yorkshire
(as will
distances
at the stations,
The Yorkshire
mining Z, and
may be
any
star in
tions
make
is
for if
deter-
Their errors
the observations of
X too small, the same observaY equally too large, and in forming Z=X+ Y
Yorkshire
make
here
all for
completely omitted.
totally
In
fact,
the determination of
independent of those of
investigation of its
depend on those of
mean
X and
Y; and the
X and
Y.
It will
C2
COMBINATION OF ERRORS.
3G
of
will
Shetland
Z= X+
Thus
only.
may happen
it
although
that,
Z is less
probable error of
The
only,
common
to
4G.
W=X Y;
or probable error of
required to
error
W.
The fundamental
supposition,
is
is
it
X and
frequency
when a
two or three
that the
is,
for positive
and
And
is
law of
implied in our
final
+ Bx,
of the
same magnitude.
namely,
Aj
and
for
positive
jp
c2
= s.
Bx,
Inasmuch therefore
and negative
equal numbers,
errors as
+ Y;
this
it
follows that
Now
(p. e.
of
r
is
W= X+ (
Wf = (p.
e.
error of
Y.
of A')
=+s
liable to
liable to the
is
same magnitude
errors of the
as
for
(p. e.
of
Y)\
in
same
7
I " is
37
(p. e.
Wf =
The theorems
48.
of
(p. e.
of Article 44
e.
of
(X Y)Y =
m.
s.
of
(X
{e.
{p. e.
and. the
Y)}'
(p. e.
may
F)\
of
therefore be ex-
(m.
e.
= (e. m.
(X Y)Y =
of
X) 2 +
s.
(p. e.
of
X) +
of
X) 2 +
of
X) +
e.
of
Y)\
s.
of
F) s
(p. e.
of
Y)\
(m.
(e.
m.
for
X+ Y will be similar
49.
The
when the
We
errors of a fallible
general law of Frequency of Errors, the errors of any constant multiple of that measure are subject to the
laws
fallible
same
law.
sums and
Now
all
same
when
and multiples.
of
which we
Frequency of Errors
ficient notice,
we
fallible
shall
will apply.
Regarding
Law
of
this as suf-
Frequency of Errors.
quantity
Law
of
COMBINATION OF ERRORS.
38
Values of
7.
Error, in
To
50.
kX+ IY,
k and
By
error of AT;
error of Y.
dent
kX=k x probable
fallible quantities,
{p. e.
of
(kX + 1 Y)}* =
of
(p. e.
kX) 2 +
(p. e.
of
Y)\
(7cX+lY)Y = k\(p.e.
of
X) 2 + 1 2
of
X) 2 +
(p. e.
of
Y)\
In like manner,
{m.
of
e.
51.
number
(kX+ I Y)f = k2
To
(m.
e.
(m.
e.
sum
of
of
F)
2
.
any
B + S+T+ U+&c.
This
is
easily obtained
of
(R +
[p.-e.of{(i2
S)}
(p. e.
+ ^) + r}]
{p. e. of (It
= (p. e.
of
of X)
(p. e.
of )
2
;
+ S)Y +
R) 2 +
(p. e.
(p. e.
of
of
S) 2 +
T) %
(p. e.
of
T) s
{p. e.
= (p.
and
so
e.
3,9
S+T)+U}Y
of
of
(R +
S+ Tff +
Rf+ (p. e.
of )
(p. e.
Uf
of
+ (p. e.
of T) +(p.
of
e.
U) 2
e.
m.
or m.
s.
e.
for p.
e.
throughout.
52.
u,
of (rR
is
+ sS + tT + u U)
Mean
Error, substituting
e.
s.
and m.
may be
U)\
m.
s,
50,
r,
e.
for p. e.
called "
Cumulative
Measures."
53.
where
To
X Xv Xv ...X
lt
nf
are
X +X
different
. . .
+ Xn
and independent
By
X
COMBINATION OF ERRORS.
40
{p.e.of
+
= (p. e.
=n
and
of
(p.e.ofX)
of A^)
(p. e.
of
A^+fc.e.
of A',)
...
+ (p. e. of XJ +
2
. . .
+ (p. e. of A^)
n terms
to
X Y;
X
therefore,
p. e. of
(X,
+ X8 + ... + XJ = *Jn
p. e. of
Xv
54.
nX = n x p. e.
p. e. of
of
x ;
of (X,
4-
+ X ) = 01
...
of
p. e.
Xv
&c.
is
equal to that of
Xv A
little
When we
consideration will
add together
first
Xv there
necessarily,
is,
X X
&c:
nx
large
error
l5
t,
is
if
is
it
sign,
and therefore
all will
it is
very improbable
is
The magnitude
mean
proportional to the
fre-
mean
error large,
To
55.
Xj =
X +X +
X +X +
error of
= p. e.
to
. ...
Xv X
where
+ Xn
..
will
terms, although.
of
...
the
n.
X=
p. e. of
make
p. e.
41
are
mean
of
different
v
and
The mean
of
J (p.
-i
(P-
J( P
and
XJ +
e f
XiY +
'
its
of
e.
X, I, ...
of
X + X2+~- + X
= p. e.
of
XY+
e of
XiY +
(p. e.
"2 (P-
. . .
+ i (p. e. of X )\
n
to
w terms,
.e.ofX ) 2 = ^(p.e.ofX r;
1
therefore,
p. e. of
mean
of
Xv X
. .
p. e. of
Xr
SRStTY
'
COMBINATION OF ERRORS.
42
8.
Instance
56.
station
of a
distance
The
(1).
colatitude of a geographical
determined by observing,
is
star
at
upper culmination
its
same
lower culmination
being applied.
observations
p. e.
To
1.
is
star at
all
and by
of colatitude.
The probable
is
mean
which
of to observations, is
ywi
mean
Now
of
n observations,
the colatitude
nith-distance
= 9 upper
which
e
tj
is
'
1*
*
zenith-distance
+^
lower ze-
Therefore,
(p. e.
by Article
of colatitude)
= - (p.
_l
e.
1
|
'
of u. zen. dist.) 2
(p.e.Ti,)'
52,
to
(p.e.l.)
4
'
(P-
e f
-
zen
dist.)
43
then
(p. e.
or
e. 1.
of colatitude)
p. e.
Instance
57.
= p.
of colatitude
(2).
= p. e.,
= ^'
''
.
= ^
( +
-)
mn
moon with
is
the
mean
to
mined.
and
if
If p.
e.
p. e.
s.
the
number
of star-observations be n, then
p. e. of
p. e.
mean
of star- transits
of moon-transit
= p.
e.
"'
,*-
m.
(moon-transit
mean
of star-transits)
we have
'
44
COMBINATION OF ERRORS.
If p.
e.
s.
= p. e. m. = p. e.,
p. e. of (moon-transit
mean
of star-transits)
amounts
little
stars.
9.
In Articles
58.
of determining the
Probable Error,
But
it
is
known.
certainly
is
measured
is
now undertake
series of
and
is
Error of
good)
is
known
(all
We
shall
Given a
the mea-
of the
59.
sult to
We
mean
of the
is
result.
;
Yet
4.)
mean
this
how much
its
chance of
And
error.
for
first,
Mean
In
Error.
error
And
the
errors
if,
is
to
this
is
different
is
+ errors,
not affected
is
sum
if,
found in
Mean
Suppose
Square.
a, b, c, d,
&c.
is
+ h + c + d + &c.
~
n
and therefore
of
2G
the
of Article
n terms
error
not be
mean +
60.
the
which
error, will
sensibly unaffected.
Error
magnitude but in
mean
Mean
the
become apparently
all
the
all
for
we form
COMBINATION OF ERRORS.
46
mean
of a,
b, c, d,
&c, but of
a+b+c+d+ &c.
,
a+b+c+d+ &c.
+ b + c + d Jr Sec
a
c
The sum
cf apparent errors)
is,
sum
the
of
is
+l +
c"
+ &c
Now,
in the long
(a
K
+ b + c + d + &e.
run of observations,
first
or o
or c
may
consider
-we
'.
'
But
for
so that for
a",
Square)* using
+b+c+d
by Article
51,
Mean Square
= (m.
n x
(e.
v
m.
(Error of
of a measure)
s.
And from
,
m.
s.
e.
m.
s.
of a
ot
And by
(e.
s. e.
m.
Square)
we form
xn x
s.
of b)
(e.
+
.
truly
is
m.
&c.
of a measure)
s.
of a measure)
2
,
2
.
this,
measure
the
+ b + c + d + &c.)
Mean
'
e.
+ (m.
of squares which
= (n 1)
p. e.
of a)
s. e.
=n x
Thus the sum
of -Error of (a
47
mean =
/sum
^
711
/sum
-
V/
.
-.
(n-
1)
of a measure
= 06745
p. e. of
the
mean
O'o/4o
sum
4
,
A /
7i
[n
=-r
1)
61.
the
will
mean
is
M.
C,
It
is
supposed
COMBINATION OF ERRORS.
48
the
First, for
mean
Select
error.
M:
number
to be
I,
the measures
all
supposing their
A + B+G+&C.
Mr
,
'
error.
Select
number
to be
all
M\
the
sup-
s,
M P+Q + B + &C.
s
mean
error
is
mean
to
error.
The mean
of
be adopted.
We
wish to form (A
2
But
= A +B*+
2
This
is
the
"Sum
C"
+ &c. - n M\
.
USE OF COMBINATION-WEIGHTS.
PART
49
III.
10.
bination-weight ;"
combination
principle
caution in
its
of most
advantageous
measures."
62.
The
numerous observations,
to
which
of two kinds.
The
First
is,
measures.
by means
of
numerous
direct
period
making
of
and immediate
direct
we
are
known
render similar
observations at an
ing
its
longitude,
stations, in order to
unknown station
we are making
stars at
and immediate
more
stations,
puted.
A.
50
63.
is,
How
It
depending
(for instance)
sum
extraction
indices of powers: or
(to
which
all
only by
its simplicity,
permits
all
of the
operations.
not
itself,
it
is
sometimes convenient),
is,
to
sum by
to divide the
the
The problem
64.
becomes
combination-weights
Arid to answer
fix
result
is:
That
correct
is
this,
The
combination
whose probable
mean square,
we can do.
of combination-weights.
of advantageous combination
What
this,
advantageous
sum
error,
or
we must
criterion
is
decide on
on which we
mean
error, or error of
We
now
be most
will
This
is
all
that
it is
many
other
probable that
it is
its
certain that,
we
this rule in a
shall
51
liable to
Now
65.
if
we know
for the
II,
we
is
weights.
and minima.
to
be made mini-
Its application
is
of complex
maxima
66.
It
sometimes happens
that,
all
or in several of the
We
shall
call
these
"entangled
to be impressed
measures."
on the reader
is,
to
be
D2
52
of each observation.
It will often
be found
that, in this
74
at
Instances
below
the simultaneous
deter-
this
of
if
stage,
be
will
to 85).
The Second
G7.
which,
so),
an early
class
is,
its
It
may be
illus-
the planet
is
orbit.
The
at
different
when
distances, observed
points
in
its
and
orbit,
in
If ap-
which
it
may
require;
it
will
it for
be possible to express, by
distance
by numerical
quantities, to
is
How
shall these
form exactly as
And
its
own
many
equations as the
number
actual
is
now,
so as to
of indeter-
of complex
This
is
53
also a case
Numerous problems
in
It will
Combination of simple measures; meaning of "theoretical weight;" simplicity of results for theoretical
11.
tween two
a priori;
Let
Supj)ose that
68.
some element
of observation
[e.g.
stars), all
method
Ev E ,...EM be the
of
of
we can judge
combining them.
measures, which are not known, but which will affect the
result.
which = e.
wv
as
w.
is
...
And
wn
Then the
ev
e2
...
en ,
each of
let
w E + w E ... + wn En
w + w + ... +wn
1
w +w
1
The
(p. e.
...+
+ wn
...
of result)
w + wz
i
2
,
'
nJ
this instance
-\
w +w
1
by Article
(w t
which in
\wt
+w
...+
52, is
+w
. . .
...
+ wny
becomes
l
tu n
+W
-&2+&C
54
Making the
fraction
2w,
W* + W* ... + W n
Similarly,
W^ + M?2
2w
w + iu
+ w*
...
It follows that
That
m/j
is,
+ wn
= 0,
=w =w
2
metical
all
are inde-
equal combination-weights;
or,
=V
or'
terminate.
= 0.
by w#
w* + w 2
and
+ wn
. . .
results
= r-
55.
may be
different
or, if
means
of different
ferent days,
tions of colatitude
of results
would have
different values.
by means
from different
The
stars will
(w x
may be
retained, rejecting
e.
w*e* +
notations of Article G8
vr*e* ...+
dif-
In determina-
w.,
-f
wn
wny
(p. e.
of result)
8
,
THEORETICAL WEIGHT.
wv w
and
55
this
minimum.
Differentiating with respect to
2"A'
*i
+ w2 ea
+ wn
wv
_1
^,
+ lU ...+Wn
tv
And
+ iv *e
'
... -I-
wn\"
J^ + w
w +w
l
...
=a
n
It
is
= w e* = &c. = w n e^ = G
2
CO
(p.e. of result)
_ C(w
70.
...+
We
of result)'
shall
now
w _
tl
(p. e.
+w
Or
some
Hence
indeterminate constant.
and
2w 2 e2*
w{e*
=0
'
C_
111
e*
e*
introduce a
H...H
en
new
term.
Let
(probable
error)*'
t.
Then we have
w.
When
independent
fallible
measures are
collateral, that
is, when each of them gives a measure of the same unknown quantity, which measures are to be combined by
final result
ADVANTAGEOUS COMBINATION OF MEASURES.
5G
The
First.
When
Second.
sure
proportional to
is
its
equal to the
When
sum of the
measures
theo-
1
.
proportional to the
number
71.
Thus,
we may com-
double stars
made on
the results
(for
(for
different stars
the results
(for
72.
moon on
In Article 56
we have found
The
reader
is
When
is,
for the
m observations
mind the
independent
fallible
fallible
quantity
'
57
its
lower culmination,
/m + n
~2\
where
mn
'
e is the
Another
star,
all being-
whose observations
/?,
+ Wj
lujT^
&c
>
in sn 2
The
'
mn
m+n
4
'
different results
mean)
with
m,n,
m +
'
nt
'
e"
2
-*-,
m +n
'
ought to be combined
combination-weights
&c.
(to
proportional
form a
respec-
tively to
mn
m+n
mna
+ n2
a
m,n,
+n
and
mn
e~
\m + n
mn
l
vn,
yi a
+n
formed will be
so
m +n
%
&c .;
'
its
is
If
it
is
becomes one of
is
"
free
from
entangled
+
ADVANTAGEOUS COMBINATION OF MEASUEES.
58
We may
73.
down
We
mum
have in Article
p. e.
Gi)
of result mini-
function
pose that
We
we use combination-weights
Put
1.
and E'
n
the p.
e.
will
n
n
for the
1.
same
e'
= 2e.
them by
But sup-
in the proportion of
actual errors
the actual
be
n+1
n+1
V e+
-
l)-
V e J e VOr + 4)
\= --nr+ r
[n
+ V-
3-2m
/f
With combination-weights
as 2
1,
the
p. e.
of result
= x
cf
o
0943.
RELAXATION OF RULE.
With combination-weights
as
4:1, the
p. e. of result
59
60
12.
74.
will
of entangled measures
Instance
station
moon
is
to
(1).
by ascertaining the
stars)
same manner
by Articles 47 and
unknown
station
is e
at a
of the times
or of
any
star to
is e
and
+
/
a/CHA
48, as these
at
station
be
e.
probable error of
57, the
station
known
is a);
moon
known
difference be-
mean
that at the
the
arid
/(-+
therefore
in
differ-
iseW^-
and
unknown
b stars at a second
station,
is
known
moon
The probable
station.
e A
+j+
is
ENTANGLED MEASURES.
Now
if
we combined
we should
of Article 70,
Gl
correct,)
by the rules
For, the
two
observations at the
To
75.
unknown
we must
In
actual errors.
strictness,
inasmuch as the
we ought to
refer to the -*
but,
inasmuch as
it is
of the
independent of
Then the
be N, A, B, respectively.
aefcfc*=eErors
paring the
of tin-
by com-
are respectively
N A, N B.
Then the
a, /3.
And
+ /3
+ j3
+ /S
K ^ + dw
e of
-
To make
this
(p e
-
0{Ay
(=.
w?
a (p.
e.
of A)'
+ /3
(p. e.
of
Bf
(p e of *>'}
-
G2
minimum.
is
is
G
R/3
"~(p.e.of)
"-fae.ofAy
G is
where
|(p. e. of
,
Nf
+
;e
(l
we put
^1
Af x(p.e. of
of
+ ^e.of^)4
2
(p.e. of
(1
If
70.
'
{(p.e.ofAT
And
an indeterminate constant.
S!
q)(l
) )
6)
of the observations
weight" of
final
n, a, b, for
those
last
11
_
1_
(a
+b
'
+ b) n
n+(a-fb)*
na
Now
if
+b
n,
'
n,b
b
,-
n.
a-t-b
N had
more complicated character may be seen in the Memoirs of the E. Astronomical Society, Vol. xix. p. 213.
* Instances of a
63
weight of their
for theoretical
result
a'n
a
r.
Da
+a
an
a
And
if
+b
n.
an
(a
'
b)
+b
N had
b'n
r,
nb + b
_bn
a
And
+b
bn
.
(a
'
b)
consequently,
ra
And
to
+b
n,,
be
it is
+ rb = r.
satisfied
77.
weight n
no other
r.
theoretical
rate parts ra
theoretical
D, &c.
rb
if
weight of result
found, applies
C,
and
there are
r.
G4<
The
78.
with
parison of
N with
Hence
AT with
A, and com-
(as
relates.
and
respectively,
is
N with
result
which
relates, or
relates is inferred
relates
whether the
is
it
JSf
following.
Instance
79.
(2).
M)
are
dian,
made with
it
&c.) are
made on
is
A, B, C,
to actual errors
different triangulation-signals
to find
azimuth
of each signal.
m m m
a,
b,
c,
&c.
m is
with
a,
with
b,
&c,
or are
bm
am
m + (a + b + c &c.)
80.
Instance
(3).
'
m + (a + b + c &c.)
&c.
f^S.
ENTANGLED MEASURES.
65
into
A A A
means
of the
first
means
of actual
suppose that
and second
errors being
actual
suppose that
b stars
respectively
B B
t
observed at the
are
and third
first
C C and
only,
d stars
the means of
that
thus
oj
Ti
o3
fc
a>
o3
3
-S
" "S
o
h -
<K
id
O _^
w
O g
m
Or^
J**
|I
U2
I02
-4 3
OQ
r
!h -w
-4^
^4 2 ,
Stars 6
Bv
Stars c
cZ
c3
aj.jj
Stars a
Stars
a
?o
"1
S
.-<
a>
x,
e.
It is
now
first
81.
first section,
OG
whole
arc.
first
section
A -A
I.
II.
Bt
A-^-(c -ay[
iv.
D - Dl -(A -A )\
D -D -{C -Cj]
V.
VI.
of these, III
a mere reproduction of I
is
IV, V, VI,
I,
\ BireCt
4, -^-(4, -4,)]
in.
But
-BJ
it is
may be
B -B
and of
one
solutions.
The following
A A
A
with combination-weight
w,
-A-C +C
3
x,
D -D -C +C
z
v,
y.
A lt C C
2
The
82.
mean
will
= -{v+x)A +vA
1
be
(B-D- C +
3
< [)
ENTANGLED MEASURES.
The independent
of resultN
we
are
fallible quantities
67
(p. e.
now
of
separated
A f= -,
l
and
find
(y
Making
this
+ w + x+yf
minimum
with regard to
v,
w, x, y, as in
Article 69,
(v
v
=
+ x)-+v'a
a
C,
11
W r +W T =
(y
+ x)
'a
(J,
+ x - + {x+y) - + (x +y)
a
C,
=g
{x+y)\+ {*+y)]+y\+y\
From which
2
_ 4a +
2ac + 4<ad
~8a +
+ 6^T
4a& + She + Sbd
b n
W ~2 C
'
- 8a + 6c + 6d n
2ac 2nd
X
~8a + Gc + 6d
6c
'
'
2ad + Scd
~ 8a + 6c + 6d
E2
68
It
is
may
be
by sub-
= b = c = d,
and
D = aC,
become
D
83.
'
we thought
If
fit
'
-A -G +G
a>
and
it
would
easily be
cd
be proportional to
a, b,
and the
theoretical weight
of the result
fa
cd
arc,
the
a -a
3
-a
84.
Now
if Ave
zv-A-'B.+tfi;
result
bd
2b
+ 2d.
to
form
the whole arc, and inferred the probable error of the whole
ENTANGLED MEASURES.
Article 44,
we should
69
For, the
two
sections are
the observations
A B
,
B^, C,
D D
t
The
whole
A A
3
Dj
stars,
B B + C Cr
error
1 fa
is
with error
c stars,
with
be found to be
?
If the
The
result will
tion
part.
is
L\
be obtained by
will
number
\2
+2+
be
26
+ 2c,
very small,
(as if
is
small, b
and
= 0, d
large,)
This instance
is
may be
great.
and probable
if
error.
So
to the
we
its
much
actual error,
of the actual
is
a mea-
70
if,
we simply add
we
is
very
incorrect.
85.
it
will
be best to use
amplitude
only.
clear;
7G,
its
for
must be
79,
C,
D, the operation
is
perfectly
result.
86.
It
is
The caution
which
is
required,
all
the
coefficients of
and
error,
to
and to
by a process
special
minimum
Treatment of numerous
13.
unknown
several
"
minimum
87.
The
quantities
(the
to
&c,
x, y,
&c. which
applying
equations
squares."
71
it is
number
It has there
of
which elements we
discover,
to
for clearness
shall
suppose to be three, though the investigation will evidently apply in the same form to any
corrections,) every equation will
ax + by +
where
of such
cz
=f
is
theoretically
served,
number
and
observation.
therefore subject to
If the last
we
by proper
an arbitrary number,
for
f is
made =
which sometimes
a, b,
c,f and
we
it is
We
1.
being
/2
88.
three,
The number
and
to three in
it
equations
final
suggests
by a
and to adopt
their
sum
series of factors
series of
alx
fundamental equations
+ b y + clz=f
l,
aix+bay + c^=fs
&c.
series
h^x + k&y + \c z = \f
x
h2 a 2x
y ,
+ hp y + k,c,z = k.,f
&c.
l/i.jc+l2 b 2 y+12 c2 z
= lj],
&c.
first
h1} k 2 &c,
Ave
is
secondly, to multiply
thirdly, to
itself,
&c.
2 2
2,
&c.
m, &c-
sums are
x t
(Jca)
x X
(la)
and
final
z,
for
h,
(mf).
73
I,
to ascertain the
is,
law
may
be
minimum.
89.
for a short
The
time,
process of
when
may be
how the
sums
is
by sums
in fact a collection
Let
solution
of the equations
hibited;
xX (na) = 2 (nf)
t{nb)=0;
$(nc)=0;
then the
is
thus ex-
74-
of n.
From
90.
these,
= tt / +j ,+&c..
a + n a. + &c.
p
S(n/)
'
(na)
??
z
2
1a 1
x actual error of f
+ >i a + &c
2
a +
1
n 2a 2
w x actual error
+ &c.
ofyfa2
+ &c,
and, as the probable error of each of the quantities/^,
&c.
= e,
ni
e~
(7*
= e"
The numbers
square
nv
its
+ &c
them
we put Bnt 8n 2
(if)
shall
variation produced
variations in each of
of probable error of
therefore
If
v.
"2
a +?? 2 a 2 + &c.)
1
shall
be
be
minimum
0.
and
by simultaneous small
of ordinary differentiation,
we
~0
+ n* + &c.
Wj"
n,Sn, +n
~
^
0=
l
or
8n a2
Sn
w^j
+ &c.
a,$n,
+ a Sn + &c.
+ n a + &c.
2
a8i>
'
&c.
....
rin
L1J.
here, as
and 69
for
But the
= 0, 2
(nb)
(mc)
=
=
b 8n 1
l
b 2 Sn 2
+ &c
= 0^ + c 8n +
2
[2],
&c
[3].
91.
It
We
Let h = av
the conditions.
m =b m =b
1
to ex-
require.
tract analytically
&c.
we
for
shew
numbers n v n 2
k2
=a
2>
synthetically that a
&c.
&c. satisfies
=b
b &c;
2
x t
+ y.S
+ z.X
=2
(a/)
[4],
+ y.Z(b"~)+z.Z(bc)=S(bf)
[>],
x.Z(ac)+y.Z(bc)+z.Z(c*) =S(c/)
[6].
(a
x.S(ab)
Then the
(ab)
values of
x, y, z,
(ac)
7f>
multiplying the
by
third
being
r,
[p
first
by
of these
+q 2
.
coefficients of
q,
the
y and
.3
Then
to vanish.
(a
the second by
p,
made
x x
we
92.
+r 2
(a b)
(ac)}
+ 2.X(6s) + r.S(&c) = 0;
+ ^. 2 (Jc) + r.2
(c)
(c
=0;
xx 2
(a
2{c(pa + qb + rc)} =
[9].
now
+ re.
replaced by
pa +
qb
=2
{(pa
+ qb + re)
(n~)
= p 2 (an) + q 2 [b [pa + qb +
.
The
last
of Article 89, n
Therefore
re) }
{pa
+ qb + re)}
+ r 2 (c (_/; + qb + ?*c)j
.
(n
2
)
=p. 2
denominator of equation
[8]
Substituting
(an).
[1],
the equation
becomes
("i~2 Kl i) & n i
or
(#&,
+ 7'oJ
r
or
Bn 1
q
iV(bSn.l
'
1+ r (cjw,
b9Sn92
'
c8s
^n2
Sna
+ &C.))
,
+ &c.)J
+ ^ c = 0>
4- &c. =
-
[10];
is,
equation
[1],
validity of the
is
true
one
Now
new assumptions.
hand
=0
by equation
consists of
[2],
taneously satisfied
and
will
two
parts, of
the
which
by equation
therefore
depend the
[3].
7/
are simul-
assumption of
is
minimum.
If
93.
we
investigate,
by a
is
and
z,
manner
as for
a;;
that
is,
z,
and
is
z,
minimum.
in the
same
result for
The problem,
same
y,
for
same manner,
is
axx
+ l y + c z =fv
aax
&c.
78
is
x 2
.
a?
(a
(aft)
{ah)
iac)
=2
(a/),
+y 2
(//)
+2.2
{bo)
=2
(*/),
(Jc)
=2
(</).
+y 2
(ac)
Suppose
94.
+y 2
.
2
(
x, y, z, shall
condition
sum
that the
and
z,
deduced values of
x, y,
or
^.{ax + hj + cz-fy,
shall
On
be minimum.
with respect to
each equation
differentiating
x,
obtained
2
and similarly
[a
for
{ax
y and
+by + cz -/)] =
Z{b.{ax + by + cz-f)}=0,
%{c.{ax+hj + cz-f)}=0;
the very same equations as those found above.
In conse-
x, y,
and
z,
that the
sum
of squares of errors
method
is
squares."
This term
is
very unfortunate
it
minimum
has
fre-
minimum
presented
is
sum
the
whereas
discordances,
it
when
79
so multiplied as to
probable error.
It
95.
is
when
the
number
of
restricted to three,
is
unknown
obtained,
is
is
universal;
multiply every equation by such a factor that the probable error of the right-hand term will be the same for
all
of one
unknown
equation
and
so
on
coefficient
its
sum
second unknown
unknown quantity
for a
new
quantity
unknown
quantities.
96.
determined,
cess.
It
we may proceed by
will
We
it
leads to
would recommend
(that quantity
SO
93,
will eliminate
y and
They
z.
to be,
For equation
[4],
For equation
[5],
For equation
[6],
There
number
trouble
no
is
ac x
& x 2 &c
.
ab x
ac
"Z
c\
x2. b".
so great that
is
S be 2
when the
unknown
of
it
will always
but the
be best to use
numbers.
Applying
these,
we
obtain
x = P.%(af)
where P,
+ Q.^(bf) + R.t(cf)
cf,
Now
if
quantities
f f
lt
in
we
(pfli
+ Qh + Bc^f +
t
We have
here a
number
(Pa,
Qb,
we
+ Bc& f + &c.
r.oixj
(Pa,
is
if
shall find
tities, to
apply.
will properly
+ Q\ + Re,) 3 +
= z.(ra + Qb + iicy;
(Pa,
+ QK + PcJ + &c.
may
which
but which
by an
will
would be exactly
The
97.
which in reference
is
By taking advantage of
may sometimes be materially
In prac-
striking
off,
produce different
certainly
The use
results,
of
but not
necessarily
if
and
quantities,
tice, all
by
unknown
theoretical reason.
diminished.
is
same
for the
y and
similar.
b 1}
PERMITTED. 81
it
The operation
s
IS
we repeat the
are,
minimum
will furnish us
on the whole, a
factors.
little
smaller
82
14.
It will perhaps
98.
tions,
we
will take
two instances
arise.
99.
It is required to
1.
equations between a
number
C,
of transit observers
A, B,
many
(ab) to
and B, and
AB
parisons.
And
and B, (AB)
single comparison
is
for its
is e.
Therefore
error of
(AB)
A-B = (AB),
in
which the
e
,
/(ab)
last
we must,
term
srm
is
liable to
tc the probable
error
by
*J(ab),
and then
e.
Thus we
find,
83
for the dif-
same probable
error e
V(aj)
V(c)
A - s/(ab) B = sjiab)
A - *J(ac) G = V(c)
(AB),
(A C),
(J5C),
&c.
Vt&c)
B-*J(bc)
C= V(6c)
&c.,
tions
Thus we
The
find
first
in Article*
equation
be formed by the
is to
sum
of the
following,
(ah)
(ac)
A - (ab) .B = + (ab)
A - (ac) C = + (ac)
.
(AB),
(A C),
&c.
is
to be
the following,
(ab)
B - (ab) .A = -(ab).
(bc).B-(bc).
(AB),
C= + (bc).(BC),
&c.
F 2
84
rule
its
observers
number
by
of compari-
sum
of all the
had been
This
sons.
is,
in fact, the
same
as if the
taken.
make
the coefficient of
changing
all
all
make
if
the coefficient of
changing signs
if
necessary),
and add
all
together to form
a determining equation.
In the various multiplied equations which contain
including,
make
if
the coefficient of
changing signs
if
two
C,
series
necessary),
and add
all
together to form
a determining equation.
And
so
It will
may be
through
all
the observers.
produced by a combination of
and therefore
all
termining equations
assume a value
C, &c.
for
it
is
necessary to
Instance
85
2.
may
be considered as
at
some
have
stations, all
not
all
at
observed
some
it
stations, astronomical
required
is
to lay
down the
101.
It
is
first
And
this is
is
liable to
error from
(1)
is
is
easily formed.
But
for the
instrument,
(2)
The
azimuth
(1) error of
mate
error
between signals
others.
error of
(3)
may
of probable error.
all
other treatment,
specified.
86
The next
102.
station
we may assume,
its
is
Thus,
area
approximately known,
if
may
the triangulation
is
be supposed a plane,
for the
it is
If the triangulation
investigation to ascertain).
is
we may assume,
regarded,
for
so large
must be
With
103.
must be computed
sist
area
is
For
For 2d
For 3d
station,
station,
o^
+ Ba^ b^&b^
or
+Sa.,,
b,_,
bs
o3
Ba8
+ 8b^,
+
Bb&
&c.
(where a
Ba,
&c, Bb lf
direction of a
&c,
Bb, &c.
is
l\,
( 2
+(h-K)
-x)
'
(7
* ,
and where
all
For convenience we
Bb,
lJ
fa-ad +(K-h)
where tan
87
will
write this,
=
And
a + a,
Ba
*h -A*-
>
1st station
K - A,
iu like manner,
=C +A
3
lfi
8a 3
-A
lfi
Ba,
+ B h3
cb3
l3
Bb t
first
to error of observation),
A*
If,
K - A*
Sf'i
B*
Bh *
~B
i,*
hh i
= v* - G*'
2d and 3d
stations,
which
is
the same as
A*M -
VV
<y 3
%, and
is
88
The
= V[K-
a
+ (^
1)
vKa,-a>+(K-w (K
first
-W
~ Sai)
A+M
1A
Now
if
(Saa
Bb,).
first
=X
subject to error of
give
lfi
lfi
+ NUi
Ba x
8ba
- X12
104.
hand, a
-M
ca2
fallible,
quantity
the
first
S& x
=\- L
contains
<y a ,
the second
contains #23
X.,.
by a
whose probable
we
and we
of
unknown
stations.
have a
shall
quantities
that
is,
shall
number
to
scries of
This
equa-
series
number
double the number of
to the
105.
will well
.89
examine such an
in-
He
of the theory.
what-
its
He may
The
used.
ring-signal
it is
case
v/ill
combined
it
correction of
also
refer-
Sometimes
signals, in
which
sometimes
it
is
of observations,
it
may
In some batches
is
Whatever mea-
it will
soon
present themselves.
10G.
It
may
0,
for instance,
units of length.
measure
is
the mea-
This, however,
is
only apparent.
Any
probable error
we
is
and,
probable error,
we do
in fact
its
when
its
00
tract
number.
is
an abstract
comparable, in
strictly
The
107.
tions
solution of so
numerous a
of course troublesome.
is
It
is,
series of equa-
however, no more
And
quires.
to
it is
be considered that
it
gives to every
it
that
it
system of results
is
the
due
15.
is
it is
required
tors,
the
unknown
effects of
to
fac-
it
result
existing
among
the cor-
But there
among
/
TO SATISFY ASSIGNED CONDITIONS.
91
maintained.
Instance
(1).
On comparing
made.
+ spherical
180
equal,
it
How
is
excess, to
their
which
known
of observation being
111.
Ev E,v E
Let
first
consideration
E
E
is
e2
es .
Then
is,
to
be as small as possible,
e[
The quantity
ax-\-by-\- cz
in Article 87;
be exhibited in the
Hence we may
The
same form.
state the equations thus
E=
E = 0,
tf.>fc
0,
e2
92
solution
Now we
112.
and use
it
to eliminate
Then
i^=0, with
probable error
ex
= 0,
e,,
A-E^E^O,
es .
E.z
Here we have three equations to determine two quantities, and the process of Article 93 may be followed.,
113.
=1
!-
e3
e3
e3
Ev
by multiplying each
93
its.
coefficient of
ducts,
{ey
(?/
its coefficient
of
z,
and
WWW
&
but
may be more
completely.
E^ = E
-r
W e might
value,
Eliminating
from the
first
Therefore
^-^.jgr^q^ii
w+w+w
equation, by
1)4*
E-A
'
-^
\2
W+W' + to"
Instance
114.
From
(2).
which ought to be
rection
360, is 360
B to be divided
= 0,
their sum,
The equations
115.
- B how
e1
E,= 0,
e2 ,
K=
en .
0,
be
E^E.^&c. + E^B,
the last of the equations
is
changed into
B E E &c En_ = 0,
1
en
and a similar
result is obtained
namely,
the
corrections
95
to
The next
116.
instance will be
Instance
(3).
more complicated.
tri-
to
is
observed independently;
which ought
be made to each.
their corrections
sought be
(1),
[1],
[2],
(2), &c.
06
= 0,
[2] =
[1]
equations,
(2);
[18]
And now
unknown
(1),
= 0,
(18).
Ave
by virtue of the
geometrical relations.
117.
[2]
Then
[3]
+ [4] + [5] +
[G]
= a known
quantity A:
known quantity
+ [9] + [10]
[3] + [H] + [12]
[4] + [13] + [14]
[5] + [15] + [10]
[6] + [l7] + [18]
When
we
D,
E,
F,
G.
that they
B,
C,
[2]
plied,
and
300,
fill
up 360
and which
so adhere together
nevertheless
might happen
d from
c,
from
that, in calculating b
d,
from
from
But
a.
it is
a, c
f,
from
b,
we should
necessary that
a.
lations
from
and a from
e,
97
it is
sin 9
sin 8
sin
10
sin 11
sin
13
sin
sin 12
sin
14
sin 16
15
sin
17
sin 18
log sin 7
.
log
sin 8
+ log
sin 9
log
sin
10
+ log
sin 11
+ cot7
x[7]
-cotSx
[8]
+ cot9x [9]-&c
+ cotl7x [l7]-cotl8
=
We
x [18]
0.
this expression,
which
symbol
is
known
quantity.
By means
fied.
quantities
tities to
118.
[1],
of these,
[2],
we
be rigorously
to
satis-
Suppose
for instance
&c, as
[2]=
we
far as [8].
We
have
C- [9] -[10],
[3]=D-[11]-[12],
A.
98
[4]
='-[13] -[14],
= ^-[15] -[16],
[6] =-[17] -[18].
[5]
equation,
first
[\]=A-C-D-E-F-G
+ [9] + [10] + [H]+[12]+[13]+[14]+[15]+[16]+[l7]+[18].
Then
[7]
= -[l]-[8]
=-A+B+C+D+E+F+G
-[8]-[9]-[10]-[ll]-[12]-[13]-[14]-[15]
_[1G]_[17]-[18].
Substituting this in the last equation of Article 117,
L + cot 7 x
(-
A + B + C+ D + E+ F+ G)
-cot7x{[8]+[9]+[10]+[ll]+[12] + [13]+[14]+[15]
- cot 8
[8]
-cot 12 x
+ cot
15 x
-cot 18 x
From
+ cot 9
+ cot
[15] - cot
[12]
[9]
- cot
+ [17]
10 x [10]
+[18]}
+ cot 11
x [11]
+ cot 17
x [17]
[18].
[16]
Thus
is
And
is
found in terms of
found in terms of
all
pressed in terms of
the corrections
[9], [10]... [18],
[9], [10],
it
in the preceding
[9],
substituting
[1],
[2], ...[8],
are ex-
119.
[1]
of probabilities are,
[2]=0
(1),
(2),
[18]=0
Of
99
(18),
now be changed
into the
following
[9]
[10]+...
+ [18] = -vl+
C+D + E + F+G,
with probable error
(1)
C,
(2)
[11]
+ [12]=2>,
(3 )
[13]
+[14]=^,
(4)
[15]
+ [16]=^
(5)
[17]
[9]
("series
[10]
[18]
of multiples]
G,
r
(6)
series of
]
known
|of[9],[10]...[18],U
[
expressing [7]
series of multiples')
(7),
(quantities!
r
series of
]
i of[9],[10]...[18],l = i known
expressing [8]
= 0,
(8).
[quantities'
will retain their simple form,
(9),
[10] = 0,
(10),
= 0,
(18).
[18]
G 2
100
Each
120.
be divided by
is
then to
its
= i;
[9]
(i)
[10]
[18]
_ -A + C + D+E+F+G
"
(1)
W
and so through
The
'
(2)'
(2)
1.
the equations.
all
error, are in
fit
method
of
Article 93.
The
the coefficient of
ducts
first
[9] in
[10]) will
the values of
[9],
From
121.
are -found.
It is particularly to
such quantities as
[1],
[2],
must be
error will be
remarked
we
eliminate
(2),
in Instances (1)
and
(2).
The complete
solution
is
101
so troublesome that
practice.
it
Probably some
accuracy
(2),
and
fol-
lows.
Apply the
last
for dividing
A'
(the discordance at
may be
...
G'.
necessary.
And
PART
IV.
16.
existence of
he recognized,
values.
When
123.
made, day
which
is
successive
either
series
of
observations
are
it will
one day
differs
result
obtained on
for,
It
is
our business
of,
now
to consider
such constant
The
124.
103
is,
When
made on
observations are
fact, of
The
constant error.
to a
"run
bable.
not ex-
is
If this
is
is sufficiently
pro-
series,
More extensive experience, however, may give greater confidence to the assumption of constant errors and then the
;
treatment of which
we proceed
apply.
125.
there
is
is
be established that
left.
It does not
entertain
it.
we
are driven to
it
by considerations
It is evident
may
104
Now
126.
separately, and,
let
Gl, investi-
We may
measure.
(the
we can
errors,
we
each day;
these,
with greater
and we
shall
have a
final
Article
55,
Eesult
;" still
The
"
From
this
we
can,
by the
rule
of
is
given by the
mean
of deter-
We
compound
days
quantities, numerical
and symbolical,
for all
the
"
number
any modifying
may
is
The
to
"
105
mean
This
Final Result"
remainder
is
it
consists of
series of multiples
of
all
Now
the Discordance
treat
by the
(consisting
of the
of symbols) as being
"
Mean
Discordance
"Mean
Dis-
accompanied with a
"Actual Error."
an independent
series
of multiples of symbols
of
fallible
is
of
two
parts,
(1)
(2)
A
A
namely,
numerical value.
error in the
And now
it
judgment of
(1)
or not.
just found,
is
to
be adopted
for
Mean Discordance
no
106
that
it
is,
assumption of a Discordance,
of a Constant Error.
If (2)
is
much
less
than
(1),
assumed
and
to exist,
adapted for
Mean
(1)
or
by 08153,
may he
by multiplying
as in Article 31.
130.
it
Discordance.
mere
tool
mind.
125,
These investigations
rule.
suppose that
the
"Dis-
know
But
if
there
for instance, if
we
as,
it
will
The observations
of each
son's observations, a
Mean
Mean
107
The
or required.
investigation
is
Difference
And
of Results,
the result
is
admissible
is
a Simple Personal
last,
because
it is
a Con-
Treatment of observations when the values of ProError for different groups, and probable
17.
bable Constant
When numerous
and extensive
series of observa-
sufficient to
is
in fact
We
made
it is
are not
Second
as
it
under the
two
classes,
108
by an operation analogous
the errors are only of one
In the
133.
first
to those
class.
group of observations,
the actual
let
group
in the third
of each being
group
And
c.
being
And
e.
let
cessive groups be
be
1}
z
z
x %, t 3
E E
X ,
jn,
&c;
n,
z
2 v
Ev E E
&c.
number
the
C, &c.
fir^st
successive observations be
3>
&c.
for those in
&c.
z
2 2
z
2 3
&c.
xt
z2
z3
&c.
and
Then
&c.
&c.
And
109
combining the separate measures with the combinationweights above given, will be the fraction, whose numerator
is
(a +
A+ A + &c
+ (A.
-)
i#+ (a + a + &c
+ <a-A+a-A+&.)
+ (A>*^i + :* + **) + *
and whose denominator
is
The square
134.
result,
(A)
(A)
+ & c.}
{(A
+ A + &c + (A +
This
is
to
+ {(^Y +
z
s
-2>
making each
is
*2
-)
2
.
&c &c
-
+ &c.}
preced-
is
Z
9 i>
/2 )
(,
all
sx
z# &c,
Differentiating with
differential coefficient
in former instances,
we
= 0,
z v z 2
&c,
respect to each,
and treating as
find successively,
an indeterminate constant),
(putting
for
'
110
zx
First,
Second,
n. x z.c
n. 2z.c
n. 3 z.c
z%
= &c.
~3
we may use
z.e
= A,
= A,
= A,
z.e
z.e
ii
the symbol
z.
&c.
_A_
xZ
which
n
x
+e
2 '
is
first
group
A
which
group
is
;
and
so
on through
135.
y /
.
the groups.
all
2
.
=A
c~
+ &c. +
(x
square of
for the
&c, we
insert
+ ji
2
.
and
+ &c.
+ &c),
+ ^c
2
-)
A
n
x
z,
becomes
it
2
.
z
z
x x, x 2
if for
z
x
ji
+ &c.
to
z,
z,
Ill
1
77
Vt-5 + &C.
Or
136.
If,
as in Article 131,
upon some
fix
group,
Error,
we
distinct cause of
-\
conceive that
the Constant
may
then be reduced
group so cor-
of the Constant
to
is
Let A, B,
liable to error.
errors,
and
a, b,
c,
C,
we
D, &c.
d, &c.
for
we can
the
cor-
The
+ &C.
A--J3+C+D
ii
be
V?
b~
+ <y + d~ +
(n-lf
&c.
112
CONCLUSION.
But the
actual error
its
B+G+D + &C.
+ c + d* + &c. \
2
ft*
In
fact,
sults,
by referring that
and
(n-iy
result to the
But
if,
Error and of
its
perly applicable.
These
various assumptions
ficulty in
made
little dif-
of them.
CONCLUSION.
137.
Errors of Observations and of the Combination of Observations which have fallen under our notice, the following
are the principal sources of error and inconvenience.
ERRORS TO BE AVOIDED.
113
(1)
by a method
minimum
of "
and an erroneous
result has
been deduced.
The
minimum
tained
for
squares
"
minimum
which
is
(2)
probable error of
final result,"
been treated as
result has
(3)
minimum
been
if
inferred.
possessing
We
all
when simple
factors
desirable accuracy.
believe that,
by avoiding these
errors,
and by
the Theory of
made a
APPENDIX.
PRACTICAL VERIFICATION OF THE THEORETICAL LAW
With
&x, I
collected the
of
all
if all
"
mean "
positive "difference"
3"*51.
was-215"
88,
These
may
be considered as
errors
(the
APPENDIX.
small discordance between
the
in
succeeding
215"-88 + 213"-73
-^rp;
ooo
them
decimal
was
115
The
places).
* eK
= -0755
mean
,.,
error
or
to be 1" 1973,
,
and the
The errors were then divided into small groups, each group
extending over an error-range of 0" 05 ; from 0" 03 to 0" 07,
#
0"*08 to 0" 12, 0"-13 to 0""17, and so on, both in the positive
-
and
from - 2"-38 to
The only
result extracted
in each group
of observations
and
this
was considered as
For those
variable 0""65.
cases in
make
it
extending from
range of 0""25,
actual
number
number of
2"'38
or five
to 2"-13,
obser-
make
it
2"
30.
APPENDIX.
116
was no marked
dis-
the
first
to the third,
first
and
so throughout.
without change.
sentation,
in
"difference," or error of
the corresponding
number
Then
for error
might be taken
as 124.
<?
evidently =124,
it
where
= Modulus
(1
frequency = 124 xe
1973)
or
log.
frequency =2-0934217-
^^r^
x (Error)
2
.
<fcc.
to 1-G5,
and then
05,
APPENDIX.
The comparison of the observed and the
is
Observation.
of
Error
117
theoretical results
APPENDIX.
It is evident that the
119
all practicable
all
is
or THE
'IYERSITY
or
C. J.
the
and
thereby
established.
CAMBRIDGE: PRINTED BY
/<
RETURN
TO^
CIRCULATION DEPARTMENT
202 Main Library
LOAN PERIOD
HOME USE
U.C.
BERKELEY LIBRARIES
0021050303
*$**jr
'
$$ti'fiy.*4