Beruflich Dokumente
Kultur Dokumente
Explain and
illustrate each class?
Errors are classified into two types:
Determinate errors (or systematic errors)
Indeterminate errors (or random errors)
DETERMINATE ERRORS
Those types of errors for which atleast in principle a definite cause of source
can be observed are known as determinate type of error. With proper
precaution, elimination of these type of error is possible. Determinate error
are generally unidirectional. They can be of considerable magnitude. As a
result these error can affect the measurement being made. Determinate error
are reproducible and to a certain extent in some cases, predictable as well.
Types of determinate errors: Instrumental errors: use of a measuring device or an instrument
forms an integral part of the measurement. The instrumental error may
arise due to the instrument itself or due to the effect of the
environmental factors on the instrument
Uncertainty in the last digit of a measurement: due to the least count
of the instrument. Least count of an instrument is defined as the
minimum value that it can measure each measuring device possesses a
least count. Least count of an instrument introduces an uncertainty in
the last digit of the measured value. This uncertainty is inherent and
cannot be avoided.
Poorly calibrated glassware and instruments.
Improper response: every instrument is made to work under optimum
conditions. For proper response of the instrument it is necessary.
When optimum conditions are not maintained, the response may not
OR
Relative error
the absolute or mean expressed as a
percentage of the true value is the
relative error.
R.E= Absolute error/ true value
Constant error
The absolute value of constant error
is independent of sample size.
Absolute error remains same but
relative error increases as the sample
size is decreased.
Proportionate error
The absolute value of a proportionate
error is dependent of sample size
The relative error remains constant
but absolute error increases as the
sample size is increased
Absolute error
Relative error
relative error.
0.00003450000
-9,876,543,210
1.222 x 10 6
1.22200000 x 10 6
3.45 x 10 -5
3.450000 x 10 -5
-9.87654 x 10 9
-9.876543210 x 10 9 10
-0.0000000100
-1 x 10 -8
-1.00 x 10 -8
significant
figures)
23.643
(5
significant
2.
319.15 - 32.614 = ?
3.
ANSWER
KEY
TO
SAMPLE
SIGNIFICANT FIGURES:
1.
PROBLEMS
ON
2.
3.
OR
The Standard Deviation is a measure of how spread out numbers are.
STANDARD DEVIATION:
1-The Standard Deviation is a better way to measure variation. First, we
look at the difference between each data value and the mean:. Then, to make
sure all the distances are positive, we square that difference:. Next, we add
up these differences for all of the observations: . Finally, we divide by (n
1) and take the square root to in some way undo the squaring from before.
This gives the formula: . Standard Deviation is denoted s, and it is in the
same units as the observations in the data set.
2-The Variance is the square of the standard deviation, s2. Since its units
are in squared units of the original observations, its value is harder to
interpret than standard deviation. As a result, it is not used as much.
Example
Consider the data set 1 2 3 4 5. We see that . Lets find the range, standard
deviation, and variance.
Range = Maximum Minimum = 5 1 = 4.
To find standard deviation, we can use a table to calculate each part
separately.
Sum
xi
1
2
3
4
5
---
4
1
0
1
4
10
Sum
xi
1
2
3
4
5
---
4
4
0
4
4
16
In this data set, the variance is . So we see that the second data set has more
variation than the first one, which makes sense. The observations are spread
further away from the mean than in the first set of data.
Some Notation
In a sample, the standard deviation is denoted s and the variance s2.
In a population, we call the standard deviation (sigma) and the variance 2
(sigma squared).
Formulas
SEEMA TAMBE
1.EXPLAIN HOW STANDARD DEVIATION (S) IS CALCULATED?
Ans: The standard deviation (S) is defined as the sum of squares of
deviations of individual measurement from the mean of the set is divided by
the number of the degree of freedom and then the square root of this term is
obtained
Standard deviation (S) is expressed as
Standard deviation (S)can be estimated from spread or range (w)of the set by
using equation
S=w/d
Where d is statistical factor
S=Standard deviation can be estimated by using equation
S=W/N
Where N is Total number of the measurement
2.Q-Test
Ans:The Q-test is one of the most statistically correct criteria used for
rejecton of doubtfull data
Scope:It doesnot require large no of measurement in the set
Applications:First arrange all the measured value of the set in their
increasing order
Find the spread or range of set thus arranged
Find difference between doubtfull measurement and its neighbouring
measurement
sDivide these difference by spread of the set
This gives Qs calculation:
T test
A statistical examination of two population means. A two-sample t-test
examines whether two samples are different and is commonly used when the
variances of two normal distributions are unknown and when an experiment
uses a small sample size. For example, a t-test could be used to compare the
average floor routine score of the U.S. women's Olympic gymnastic team to
the average floor routine score of China's women's team.
Chi 2 test
Pearson's chi-squared test is used to assess two types of comparison: tests of
goodness of fit and tests of independence.
A test of goodness of fit establishes whether or not an observed frequency
distribution differs from a theoretical distribution.
A test of independence assesses whether paired observations on two
variables, expressed in a contingency table, are independent of each other
(e.g. polling responses from people of different nationalities to see if one's
nationality is related to the response).
The procedure of the test includes the following steps:
Calculate the chi-squared test statistic, , which resembles a normalized
sum of squared deviations between observed and theoretical frequencies (see
below).
Determine the degrees of freedom, df, of that statistic, which is
Que> In replicate analysis of a metal ore the following results are obtained
sample
% of
metals
1
40.13
2
40.11
3
40.14
4
40.10
5
40.18
6
40.16
X
40.10
40.11
40.13
40.14
40.16
40.18
XX
40.13
(X-XX)
-O.03
-O.O2
0
O.O1
O.O3
0.05
O.14
(X-XX)
0.0009
0.0004
0
0.0001
0.0009
0.0025
0.0048
Std deviation=(x-xX)/n-1
=0.0048/6-1=0.03098
Que> in this six determination of ion from samples, each of which contain
320 miligram of ion. The following results were obtained.
Sample
no
Fe(found
in mg)
120
138
158
168
162
178
Mean=xi/n
=120+138+158+168+162+178/6
=154
Median= Arrange in ascending order
120,138,158,162,168,178
=158+162/2 =160
Obr no
1
2
3
4
5
6
x
120
138
158
162
168
178
Average deviation=di/n
100/6=16.66
154
(x-x)
-34
-16
4
8
14
24
100
(x-x)
1156
256
16
64
196
576
2264
Standard deviation=(x-x)/n-1
=2264/6-1
=47.581/2.236
=21.279
Range= Xmax-Xmin
=178-120
=58
The normality of solution is determined by four separate titration .The result
being 0.1541, 0.1549, 0.1539, 0.1543 .
Calculate mean,median ,range,average deviation,relative average deviation
from mean,standard deviation,variance,coefficient of variation.
CALCULATION:
1. MEAN(x) =(0.1541+0.1549+0.1539+0.1543 )/4= 0.6172/4=0.1543
2. By arranging the observed value in ascending order we get,
0.1539, 0.1541, 0.1543, 0.1549
Since there are even number of values therefore ,the meadian is the mean of
the two middle values
MEADIAN(m) = (0.1541+0.1543)/2= 0.1542
3.RANGE = 0.1549 - 0.1539 = 0.0010
4.DEVIATION FROM MEAN = (Observed value -mean)
d1 = |0.1541 - 0.1543| = 0.0002
d2 = |0.1549 -0.1543| = 0.0006
d3 = |0.1539 -0.1543| = 0.0004
d4 =|0.1543 - 0.1543| = 0.0000
5.AVERAGE DEVIATION FROM MEAN
=(0.0002 + 0.0006 + 0.0004 + 0.0000) /4
= 0.0012 /4
= 0.0003
4.RELATIVE AVERAGE DEVIATION FROM MEAN =
( Average deviaton from mean)/Mean
= 0.0003/ 0.1543
= 0.00194
5.DEVIATION FROM MEADIAN = (Observed value -meadian )
d1 =| 0.1541 - 0.1542| = 0.0001
d2 =|0.1549 - 0.1542|= 0.0007
d3 =|0.1539 - 0.1542|= 0.0003
d4 =|0.1543 - 0.1542|= 0.0001
6.AVERAGE DEVIATION FROM MEADIAN
= (0.0001+0.0007+0.0003+0.0001) /4
= 0.0012 / 4
= 0.0003
7.RELATIVE AVERAGE DEVIATION FROM MEADIAN
= (Average deviation from meadian) /Meadian
= 0.0003 / 0.1542
= 0.00194
8.STANDARD DEVIATION i=4
=(x - x)2 =(0.0012)2 = 0.00000144
i=1
= 0.00000144 /(N -1)
=0.00000144/(4-1)
=0.00000144/3
=0.00000048
= 6.9282*10-4
9. VARIANCE = ( S)2
= (6.9282*10-4)2
= 47.9999*10-8
10.COEFFICIENT OF VARIATION
= (S / X) *100
= (6.9282*10-4 / 0.1543)*100
= (44.9008*10-4)*100
=0.4490 %