Scribd
Upload
26 views24 pages

F Test

The F-Test, developed by Ronald A. Fischer, is used to determine if there is a significant difference between the variances of two populations based on sample data. It involves calculating the F ratio from sample variances and comparing it to a critical value from the F distribution. Key properties include its positive skewness, dependence on degrees of freedom, and assumptions of random sampling from normal populations.

Uploaded by

sureshvishal6
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
26 views24 pages

F Test

The F-Test, developed by Ronald A. Fischer, is used to determine if there is a significant difference between the variances of two populations based on sample data. It involves calculating the F ratio from sample variances and comparing it to a critical value from the F distribution. Key properties include its positive skewness, dependence on degrees of freedom, and assumptions of random sampling from normal populations.

Uploaded by

sureshvishal6
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 24

F Test

(VARIANCE RATIO TEST)


MEANING
 The test based on the test statistic which follows F
distribution(continuous probability distribution) is
called F-Test.
 The name was coined by George W.Snedecor, in
honour of Sr Ronald A Fischer.
 Fischer initially developed the statistic as the
variance ratio in 1920s.
 This test is applied to test whether there is any
significant difference between two population variance
based on the samples drawn from those population.
 For that purpose, we draw samples from the two
population and find variances. Let n1 and n2 be the size of
the samples and S12 and S22 be the variances for the two
samples.
 Then is called F ratio. It follows F
distribution and the test based on this statistic is known
as F test.
 In the F ratio, we always take the larger of the two
estimates in the numerator and the smaller of the two
estimates in the denomenator.
 If the computed value of F statistic is less than the
table value of F, then we conclude that the
population variances are equal or the two samples
are selected from the population with the same
variance.
Properties of F distribution
1. F-distribution curve is positively skewed towards right with
range of 0 and ∞
2. The value of F always positive or zero. No negative values
3. The shape of the distribution depends on the degrees of
freedom of numeratorV1 and denominatorV2.
4. From the above graph it is clear that degree of skewness
decreased with increase of degrees of freedom of numerator and
denominator
5. F-distribution curve never be symmetrical, if degrees of
freedom increases it will be more similar to the symmetrical
ASSUMPTIONS
1. Samples are drawn at random.
2. Samples are drawn from normal population.
3. Both the populations are independent to each other
4. The larger sample variance always goes in the
numerator to make the right tailed test, and the right
tailed tests are always easy to calculate.
USES OF F-TEST
1. To test the equality of variances of two
populations.
2. To test whether the two samples are selected
from the population with the same variance.
3. To test the equality of means of three or more
populations(known as analysis of variance).
EQUATIONS

In the F ratio we always take the larger


of the two estimates in the numerator
and the smaller in the denominator
Question No. 1
 The following table gives the number of units produced per day by two
workers A and B for number of days

A: 40 30 38 41 38 35

B : 39 38 41 33 32 39 40 34

Should these results be accepted as evidence that the two workers are
equally stable(use F Test)
Answer
Ho: There is no significant difference between variances of two
populations i.e. two workers are equally stable.
Let us first find variances of the two samples.
A
S12= ∑X2 ∑x 2
X X2
40 1600 n n
30 900 =8294 222 2
38 1444 6 6
41 1681
=1382.33 1369=13.33
38 1444

35 1225
n1s12 6*13.33 79.98
Total: Ʃ= 222 8294
n1-1 6-1 5
=16
B S22= ∑X2 ∑x 2

X X2
n n
39 1521 = 11036 296 2
38
41
1444
1681
8 8
33 1089 =1379.5 - 1369=10.5
32 1024
39 1521
40 1600
n2s22 8*10.5 84
34 1156 n2-1 8-1 7
Total: Ʃ= 296 11036

=12
Greater is the first, so first should be in the numerator of F-ratio.
Therefore,
n1s12 n2s22
F= ÷ =16/12=1.33
n1-1 n2-1
Degree of freedom=(n1-1,n2-1)= (6-1, 8-1)=(5,7)
Level of significance=5%
Table value of F=3.97
Calculated value of F=1.33 is less than the table value. So we accept
the hypothesis that there is no significant difference between variances
of two populations i.e. two workers are equally stable.
Question No 2
The standard deviation of two samples of size 10 and
14 from two normal population are 3.5 and 3
respectively. Examine whether the standard deviations
of the populations are equal ?
Answer
Null hypothesis : Variances of the o population are equal .

n1s12 n2s22
F= n1-1 ÷ n2-1

n1-1
10*(3.5) 2 14*32 13
= ÷ = =1.4
9 13 9.7
Therefore, degree of freedom=(n1-1,n2-1)=(9,13)
Table value of F at 0.05 level of significance=2.71
The calculated value is less than the table value .
Therefore ;
We accept the null hypothesis, variances of the two
population are equal and hence, standard deviation of the
two population are also equal .
Ex 3
 In a sample of 10 observations the sum of the squared
deviations of items from the mean was 101.7. In
another sample of 8 observations the value was found
to be 94.5. Test whether the difference is significant
at 5% level of significance.
Ex 1
 Two sources of raw materials are under consideration by a
company. Both sources seem to have similar characteristics,
but the company is not sure about their respective
uniformity. A sample of ten lots from sources A yields a
variance of 225 and a sample of eleven lots from source B
yields a variance of 220. Test the equality of variance at 1%
level of significance.
 Ans: F=1.03,TV=4.95 Ho accepted
Ex 2
 In a laboratory experiment, two random samples gave
the following results:
Sum of squares
Sample Size Sample Mean of deviations
from mean
1 10 15 90
2 12 14 108

 Test the equality of sample variance at 5% level of


significance
Ex 3
 A random sample of pigs fed on diet a over a
period gave the following values of X1=6, σ1=3.08,
n1=8 and another sample fed on diet B ga e the
following values X2=8, σ2=4.15, n2=5.
 Test whether the diets A and B significantly
differ( i) in their means (ii) in their variances.
Ex 4
 Two samples are drawn from two normal populations. From
the following data test whether the two samples have the same
variance at 5% level.
Sample 1 60 65 71 74 76 82 85 87

Sample 2 61 66 67 85 78 63 85 86 88 91
Ex 5
 Two samples are drawn from two normal populations. From
the following data test whether the two samples have the same
variance at 5% level.
Sample 1 66 67 75 76 82 84 88 90 92

Sample 2 64 66 74 78 82 85 87 92 93 95 97

You might also like