CHAPTER 10

NON-PARAMETRIC TESTS

A non-parametric test is a test which is not concerned with testing of parameters. Non-
parametric tests do not make any assumption regarding the form of the population. Therefore,
non-parametric tests are also called distribution free tests.
Following are the important non-parametric tests:-
1. Chi-square test χ
2. Sign test
3. Signed rank test (Wilcoxon matched pairs test)
4. Rank sum test (Mann-whitney U-test and Kruskal-Wallis H test)
5. Run test
6. Kolmogrov-Smirnor Test (K-S-test)

CHI-SQUARE TEST
The value of chi-square describes the magnitude of difference between observed
frequencies and expected frequencies under certain assumptions. χ value (χ quantity) ranges
from zero to infinity. It is zero when the expected frequencies and observed frequencies
completely coincide. So greater the value of χ , greater is the discrepancy between observed and
expected frequencies.
χ -test is a statistical test which tests the significance of difference between observed
frequencies and corresponding theoretical frequencies of a distribution without any assumption
about the distribution of the population. This is one of the simplest and most widely used non-
parametric test in statistical work. This test was developed by Prof. Karl Pearson in 1990.

Uses of - test
The uses of chi-square test are:-
1. Useful for the test of goodness of fit:- χ - test can be used to test whether there is
goodness of fit between the observed frequencies and expected frequencies.
2. Useful for the test of independence of attributes:- χ test can be used to test whether two
attributes are associated or not.
3. Useful for the test of homogeneity:- χ -test is very useful t5o test whether two attributes
are homogeneous or not.
4. Useful for testing given population variance:- χ -test can be used for testing whether the
given population variance is acceptable on the basis of samples drawn from that
population.

 
 
  
-test as a test of goodness of fit:

As a non-parametric test, χ -test is mainly used to test the goodness of fit between the
observed frequencies and expected frequencies.
Procedure:-

1. Set up mull hypothesis that there is goodness of fit between observed and expected
frequencies.

2. Find the χ value using the following formula:-

χ = Σ
Where O = Observed frequencies
E = Expected frequencies

3. Compute the degree of freedom.

d. f. = n – r – 1
Where ‘r’ is the number of independent constraints to be satisfied by the
frequencies

4. Obtain the table value corresponding to the lord of significance and degrees of freedom.
5. Decide whether to accept or reject the null hypothesis. If the calculated value is less than
the table value, we accept the null hypothesis and conclude that there is goodness of fit. If
the calculated value is more than the table value we reject the null hypothesis and
conclude that there is no goodness of fit.
Qn:- A sample analysis of examination result of 200 students were made. It was found that 46
students had failed, 68 secured IIIrd class, 62 IInd class and the rest were placed in the Ist
class. Are these figures commensurate with the general examination results which is in
the ratio of 2 : 3: 3: 2 for various categories respectively?

Sol: H : The figures commensurate with the general examination results.

H : The figures do not commensurate with the general examination results.

χ = Σ

   
 Computation of value:
O E
O E O-E O E
E
46 200 = 40 6 36 0.9000

68 200 = 40 8 64 1.0667

62 200 = 40 2 4 0.0667

24 200 = 40 256 6.4000

-16

Σ = 8.4334

χ = 8. 4334
The table value at 5% level of significance
and degree of freedom at 3. = 7. 815
(df = n – r- 1 =4 – 0 – 1 = 3)

The calculated value is more than the table value.

we reject the H
we conclude that the analytical figures do not commensurate with the general
examination result. In other words, there is no goodness of fit between the observed and expected
frequencies.

Qn: Test whether the accidents occur uniformity over week days on the basis of the
following information:-

Days of the week: Sun Mon Tue Wed Thu Fri Sat
No. of accidents: 11 13 14 13 15 14 18

Sol: H : There is goodness of fit between observed and expected frequencies, i.e.,
accidents occur uniformly over week days.
H : There is no goodness of fit between observed and expected frequencies; i.e.,
accidents do not accrue uniformly over week days

χ = Σ
 Computation of value:
O E
O E O-E O E
E
11 14 -3 9 0.6429

13 14 -1 1 0.0714

14 14 0 0 0.0000

13 14 1 0.0714
-1
15 14 1 0.0714
1
14 14 0 0.0000
0
18 14 16 1.1429
4

= 2.0000
Σ

The value of χ at 5% level of significance and

n – r- 1 = 7 – 0 – 1 = 6 d.f = 12.592

Calculated value if less than the table value.

we accept the null hypothesis. We may conclude that there is goodness of fit between
and expected frequencies. i.e., the accidents occur uniformity over week days.

– test as a test of independence:

χ – test is used to find out whether one or more attributes are associated or not.

Procedure:-
1. Set up null and alternative hypothesis.
H : Two attributes are independent (i.e., there is no association between the
attributes)
H : Two attributes are dependent (i.e., there is an association between the
attributes)

 
 2. Find the χ value.

χ = Σ
3. Find the degree of freedom
d.f. = (r-1)(c-1)
Where r = Number of rows
c = Number of columns
4. Obtain table value corresponding to the level of significance and degree of freedom.
5. Describe whether to accept or reject the H . If the calculated value is less than the table
value, we accept the H and conclude that the attributes are independent. If the H  and
conclude that the attributes are dependent.
Qn: The following table gives data regarding election to an office:-
Economic Status
Attitude towards election
Rich Poor Total
Favourable 50 155 205
Non favourable 90 110 200
Total 140 265 405
Is attitude towards election influenced by economic status of workers?

Sol: H : The two attributes, election and economic status are independent.
H : The attributes, election and economic status are dependent.

χ = Σ
Observed frequencies are 50, 90, 155 and 110

Computation of expected frequencies (2 2 contingency table)

Economic Status
Attitude → Rich Poor Total
towards election ↓
Favourable = 71 = 134 205

Not favourable = 69 = 405 200

Total 140 265 405

 Computation of value:
O E
O E O-E O E
E
50 71 -21 441 6.21

90 69 21 441 6.39

155 134 21 441 3.29

110 131 -21 441 3.37

Σ = 19.26

Table value of χ at 5% level of significance for 1 d.f. is 3.841 (d.f = (2-1)(2-1)=1.

Calculated value is greater than the table value. we reject the H .

Election and economic status are not independent (i.e., dependent)

Qn: In a sample study about the tea habit in two towns, following date are observed in a
sample of size 100 each:-
Town –A:-
51 persons were male, 31 were tea drinkers and 19 were male tea drinks.
Town – B :-
46 persons were male, 17 were male tea drinkers and 26 were tea drinkers.
Is there any association between sex and tea habits ?
If so, in which town it is greater?
Sol:- H : The two attributes, sex and tea habits are independent.
H : The two attributes sex and tea habits are dependent.
Town A:-
2 2 Contingency table of observed frequency

Sex
Male Female Total
Tea habits
Tea Drinkers 19 12 31

Not tea drinkers 32 37 69

Total 51 49 100
 Computation of expected frequencies (2 2 contingency table)
Sex →
Male Female Total
Tea Habits ↓
Tea Drinkers = 16 = 15 31

Not tea drinkers = 35 = 34 69

Total 51 49 100

Computation of value:
O E
O E O-E O E
E
19 16 3 9 0.5625

32 35 -3 9 0.2571

12 15 -3 9 0.6000

37 34 3 9 0.2647

Σ = 1.6843

Degree of freedom = (c-1)(r-1) = (2-1)(2-1) = 1

Table value of χ at 5% level of significance for 1 degree of freedom is 3.84. As the
calculated value is less than the table value we accept the null hypothesis in case of Town A. In
other words, sex and tea habits are independent (not associated) in Town A.
Town B:-
Contingency table of observed frequencies

Sex →
Male Female Total
Tea habits ↓

Tea Drinkers 17 9 26

Not tea drinkers 29 45 74

Total 46 54 100
 Computation of expected frequencies (2 2 contingency table)
Sex →
Male Female Total
Tea Habits ↓
Tea Drinkers = 12 = 14 26

Not tea drinkers = 34 = 40 74

Total 46 54 100

Computation of value:
O E
O E O-E O E
E
17 12 5 25 2.083

29 34 -5 25 0.735

9 14 -5 25 1.786

45 40 5 25 0.625

Σ 5.229

Degree of freedom = (2-1)(2-1) = 1

The table value of χ at 5% level of significance for 1 degree of freedom is 3.84. As the
calculated value is more than the table value, we reject the H . In other words, attributes sex and
tea habits are not independent (i.e., associated) in Town B.

– test as a test of homogeneity

χ – test is used to find whether the samples are homogeneous as far as a particular
attribute is concerned.
Steps:
1. Set up null and alternative hypotheses:
H : There is homogeneity.
H : There is no homogeneity (heterogeneity)
 2. Find the χ value.

χ = Σ
3. Find the degree of freedom

d.f. = (r-1)(c-1)

4. Obtain the table value

5. Decide whether to accept or reject the null hypothesis.

Qn: From the adult population of four large cities, random samples were selected and the number
of married and unmarried men were recorded:
Cities
A B C D Total
Married
137 164 152 147 600

Single 32 57 56 35 180

Total 169 221 208 182 780

Is there significant variation among the cities in the tendency of men to marry.
Sol:- H : The 4 cities are homogeneous.
H : The 4 cities are heterogeneous.

Computation of expected frequencies

Sex →
A B C D Total
Married Status ↓
Married = 130 = 170 =160 =140 600

Single  
= 39 = 51 = 48 =42 180

Total 169 221 208 182 780

 Computation of value:
O E
O E O-E O E
E
137 130 7 49 0.3769

32 39 -7 49 1.2564

164 170 -6 36 0.2118

57 51 6 36 0.7059

152 160 -8 64 0.4000

56 48 8 64 1.3333

147 140 7 49 0.3500

35 42 -7 49 1.1667

Σ 5.8010

Degree of freedom = (r-1)(c-1)

= (2-1)(4-1) = 1 3 = 3
The table value at 5% for 3 d.f. = 7.82
As the calculated value χ is less than the table value, we accept the H . The cities are
homogeneous. So we conclude that there is no significant variation among cities in the tendency
of men to marry.

– test for Population Variance:

χ – test can be used for testing the given population when the sample is small.

Steps:-

1. Set up null and alternative hypotheses:

H : There is no significant difference between sample variance and population
variance.
H : There is significant difference between sample variance and population
variance.
 2. Find the χ value.

χ =
Where = Sample variance
= Population variance

3. Find the degree of freedom

d.f. = n-1
4. Obtain the table value
5. Decide whether to accept or reject the null hypothesis
Qn: The standard deviation of a sample of 10 observations from a normal
population was formed to be 5. Examine whether this is consistent with
the hypothesis that the standard deviation of the population is 5.3.

Sol: H : There is no significant difference between sample standard deviation

and population standard deviation.
H : There is significant difference between sample standard deviation and
population standard deviation.

 
χ = = = = 8.8999
. .

Table value of χ at 5% level of significance of 9 d.f. = 16.9 calculated value of χ is less

than the table value , we accept in null hypothesis. So we conclude that there is no significant
difference between sample variance and population variance.

Limitations of Chi-square tests:-

1. It is not as reliable as a parametric test. Hence it should be used only when parametric
tests cannot be used.
2. χ value can not be computed when the given values are proportions or percentages.

WILCOXON MATCHED PAIRS TEST

SIGNED RANK TEST

Signed rank test was developed by Frank Wilcoxon. It is an important non-parametric

test. This method is used when we can determine both direction and magnitude of difference
between matched values.
 Here there are two cases:-

a) When the number of matched pairs are less than or equal to 25.

b) When the number of matched pairs are more than 25.

Case:1

When the number of matched pairs are less than or equal to 25

Procedure:-
1. Set up null hypothesis:
H : There is no significant difference.
H : There is significant difference.
2. Find the difference between each pair of values.
3. Assign ranks to the differences from the smallest to the largest without any regard to sign.
4. Then actual signs of each difference are put to the corresponding ranks.
5. Find the total of positive ranks and negative ranks.
6. Smaller value, as per steps 5 is taken as the calculated value.
7. Obtain the table value of Wilcoxon’s T-Table.
8. Decide whether to accept or reject the null hypothesis.

Qn: Given below is 16 pairs of values showing the performance of two machines A
and B. Test whether there is difference between the performances. Table value of
‘T’ at 5% significanterd is 25.

A: 73, 43, 47, 53, 58, 47, 52, 58, 38, 61, 56, 56, 34, 55, 65, 75
B: 51, 41, 43, 41, 47, 32, 24, 58, 43, 53, 52, 57, 44, 57, 40, 68

Sol: H : There is no significant difference between the performance of 2

machines.
H : There is significant difference the performance of 2 machines.
 1 2 3 4 5
Machine Machine Difference Rank of Difference Rank with signs
A B (3) = (1) – (2) (without signs) + Sign - Sign
73 51 22 13 13
43 41 2 2.5 2.5
47 43 4 2.5 4.5
53 41 12 11 11
58 47 11 10 10
47 32 15 12 12
52 24 28 15 15
58 58 0 - -
38 43 -5 6 - -6
61 53 8 8 8
56 52 4 4.5 4.5
56 57 -1 1 - -1
34 44 -10 9 - -9
55 57 -2 2.5 - -2.5
65 40 25 14 14
75 68 7 7 7
Total 101.5 -18.5

Calculated value of T = 18.5

Table value of Wilcoxon’s T table = 25
As the calculated value is less than the table value we accept the null hypothesis. i.e.,
there is no significant difference between the preference of machines A and B.
Case :2
When the number of matched pairs are more than 25
Procedure:-
1. Set up null hypothesis:
H : There is no significant difference.
H : There is significant difference.
2. Find the difference between each pair of values.
3. Assign ranks to the differences from the smallest to the largest without any regard to sign.
4. Then actual signs of each difference are put to the corresponding ranks.
5. Find the total of positive ranks and negative ranks.
6. Apply Z test and compute the value of ‘Z’
Z=

Where T = Smaller value as per steps (5)

U=

7. Obtain table value of Z at specified level of significance for infinity degrees of

freedom.
8. Decide whether to accept or reject the null hypothesis.
 CHAPTER 11
ANALYSIS OF VARIANCE

Definition of Analysis of Variance

Analysis of variance may be defined as a technique which analyses the variance of two or
more comparable series (or samples) for determining the significance of differences in their
arithmetic means and for determining whether different samples under study are drawn from same
population or not, with the of the statistical technique, called F – test.
Characteristics of Analysis of Variance:
1. It makes statistical analysis of variance of two or more samples.
2. It tests whether the difference in the means of different sample is due to chance or due to
any significance cause.
3. It uses the statistical test called, F – Ratio.
Types of Variance Analysis:
There are two types of variance analysis. They are:-
1. One way Analysis of Variance
2. Two way analysis of Variance
One way Analysis of Variance:
In one way analysis of variance, observations are classified into groups on the basis of a
single criterion. For example, yield of a crop is influenced by quality of soil, availability of
rainfall, quantity of seed, use of fertilizer, etc. It we study the influence of one factor, It is called
one way analysis of variance.
If we want to study the effect of fertilizer of yield of crop, we apply different kinds of
fertilizers on different paddy fields and try to find out the difference in the effect of these different
kinds of fertilizers on yield.
Procedure:-
1.Set up null and alternative hypothesis:
H : There is no significant difference.
H : There is significant difference.
2. Compute sum of squares Total (SST)

SST = Sum of squares of all observations -

3. Compute sum of squares between samples (SSC)

∑ ∑ ∑
SSC =        … … … . .

4. Compute sum of squares within sample (SSE)

SSE = SST – SSC
 5. Compute MSC

MSC = =
..
6. Compute MSE

MSE = =
..
7. Compute F – ratio:
 
F=
 
8. Incorporate all these in an ANOVA TABLE as flows:

ANOVA TABLE
Source of Sum of Degree of Means square
F - Ratio
Variation Squares freedom
Between SSC C-1  
MSC = F=
Samples  

Within SSE N-C

MSE =
Sample
Total SST N-1
9. Obtain table value at corresponding to the level of significance and for degree of freedom
of (C-1, N-C).
10. Decide whether to accept or reject the null hypothesis.
Qn: Given below are the yield (in Kg.) per acre for 5 trial plots of 4 varieties of
treatments.

Treatment

Plot name 1 2 3 4
A 42 48 68 80
B 50 66 52 94
C 62 68 76 78
D 34 78 64 82
E 52 70 70 66
Carry out an analysis of variance and state whether there is any significant difference in
treatments.
Sol: H : There is no significant difference in treatments.

H : There is significant difference in treatments.

X X X X X X X X

42 48 68 80 1764 2304 4624 6400

50 66 52 94 2500 4356 2704 8836

62 68 76 78 3844 4624 5776 6084

34 78 64 82 1156 6084 4096 6724

52 70 70 66 2704 4900 4900 4356

ΣX = 240 ΣX = 330 ΣX = 330 ΣX = 400 11,968 22,268 22,100 32,400

SST = Sum of squares of all items -

= (11,968+22,268+22,100+32,400) -

= 88,736 -

, ,
= 88,736 -

= 88,736 – 84,500 = 4,236

∑ ∑ ∑ ∑
SSC =        
   

=           

= 11,520+21,780+21,780+32,000 – 84,500
= 87, 080 – 84, 500 = 2, 580
 ONE WAY ANOVA TABLE

Source of Sum of Degree of Means square

F - Ratio
Variation Squares freedom

Between 2,580 C-1= 3

MSC = =860
Samples

Within 1,656 N-C = 16 F= = 8.31

MSE = =103.5 .
Sample

Total 4,236 N-1= 19

Calculated value of F is 8.31.

Table value of F at 5% level of significance for (3.16) degree of freedom is 3.24.
As the calculated value is greater than the table value, we reject the null hypothesis. We
can conclude that there is significant difference in treatments. In other words, treatments do not
have the same effect.

Qn: The following data relate to the yield of 4 varieties of rice each shown on 5
plots. Find whether there is significant difference between the mean yield
of these varieties.

Treatment

Plot name 1 2 3 4
P 99 103 109 104

Q 101 102 103 100

R 103 100 107 103

S 99 105 97 107

T 98 95 99 106

Sol: Apply coding method. Subtract 100 from all the observations.
 X X X X X X X X
(A) (B) (C) (D)

-1 3 9 4 1 9 81 16

1 2 3 0 1 4 9 0

3 0 7 3 9 0 49 9

-1 5 -3 7 1 25 9 49

-2 -5 -1 6 4 25 1 36

ΣX = 0 ΣX = 5 ΣX = 15 ΣX = 20 16 63 149 110

H : There is no significant difference between the mean yield of different

varieties.
H : There is significant difference between mean yield of varieties.

SST = Sum of squares of all items -

= (16+63+149+110) -

= 338 -

= 338 -

= 338 – 80 = 258

∑ ∑ ∑ ∑
SSC =        

=           

=           

= 0+5+45+80 – 80
= 50
 ONE WAY ANOVA TABLE

Source of Sum of Degree of Means square

F - Ratio
Variation Squares freedom

Between SSC = 50 C-1= 3

MSC = = 16.67
Samples
.
Within SSE = 208 N-C = 16 F= = 1.28
MSE = =13
Sample

Total SST = 258 N-1= 19

Calculated value of F is 1.28

Degree of freedom is (3.16)

Table value at 5% level of significance and (3.16) d.f. is 3.24.

As the calculated value is less than the table value, we accept the null hypothesis.

There is no significant difference between the mean yield of these varieties.

TWO WAY ANALYSIS OF VARIANCE

Two way analysis of variance is used to test the effect of two factors simultaneously on a
particular variable.
Procedure:-
1. Set up null and alternative hypothesis.
H : There is no significant difference between columns.
There is no significant difference between rows.
H : There is significant difference between columns.
There is significant difference between rows.

2. Compute SST
SST = Sum of squares of all observations -
3. Compute SSC

∑ ∑ ∑
SSC =        … … … . .

4. Compute SSR

∑ ∑ ∑
SSR =        … … … . .

 
 Here ∑ X , ∑ X , etc denote the row totals

5. Compute SSE

SSE = SST – (SSC + SSR)

6. Compute MSC

MSC = =
..

7. Compute MSR

MSR = =
..

8. Compute MSE

MSE = =
..

9. Compute F – ratio in respect of columns

Fc =

10. Compute F – ratio in respect of rows

Fr =

11. Obtain the table value

12. Decide whether to accept or reject the H :

TWO WAY ANOVA TABLE

Source of Sum of Degree of Means square
F - Ratio
Variation Squares freedom
Between SSC c-1 F =
MSC =
Columns
Between Rows SSR r-1
MSE =
Residual SSE (c-1)(r-1)
MSE =
F =

Total SST N-1

 
Qn: Apply the technique of analysis of variance to the following date relating
to yields of 4 varieties of wheat in 3 blocks:
Blocks

Varieties X Y Z
A 10 9 8
B 7 7 6
C 8 5 4
D 5 4 4
Carry two-way analysis of variance.
Sol:
X Y Z X
Varieties Total X X Total
X X X
A(X 10 9 8 27 100 81 64 245

B (X ) 7 7 6 20 49 49 36 134

C(X ) 8 5 4 17 64 25 16 105

D(X ) 5 4 4 13 25 16 16 57

Total 30 25 22 77 238 171 132 541

H : There is no significant difference between blocks.

There is no significant difference between varieties.
H : There is significant difference between block.
There is significant difference between varieties.

SST = Sum of squares of all items -

= 541 -

= 541 -

= 541– 494.083 = 46.917

∑ ∑ ∑
SSC =        

=        

   
 =        

= 225+156.25+121 – 494.083
= 502.25 – 494.083 = 8.167
∑ ∑ ∑ ∑
SSR =        

=           

=           

= 243+133.333+96.333+56.333 – 494.083
= 34.916

TWO WAY ANOVA TABLE

Source of Sum of Degree of Means square

F - Ratio
Variation Squares freedom

Between SSC= 8.167 c-1= 2 MSC = . .

=4.084 F =
Columns .

Between SSR=34.91 r-1= 3 MSE =

.
= 11.639 = 6.39
Rows

Residual SSE= 3.834 (c-1)(r-1)=6 MSE = . .

=0.639 F =
.
= 18.21
Total SST= 46.917 N-1= 11

Between columns (blocks):-

Degree of freedom = (2, 6)
Calculated Value = 6.39
Table Value = 5.1433
As the calculated value is more than the table value, we reject the null hypothesis. It is
concluded that there is significant difference between blocks.
i.e., the mean productivity between blocks are not same.
Between rows (varieties):-
Degree of freedom = (3.6)
Calculated value = 18.21
   
 Table value = 4.7571
As the calculated value is greater than the table value, we reject the null hypothesis. This
means that there is significant difference in mean productivity of the varieties.
Qn: The following date presents the number of units of production per day turned
out by 5 different workers using 4 different types of machines:

Machine Type

Workers A B C D
1 44 38 47 36
2 46 40 52 43
3 34 36 44 32
4 43 38 46 33
5 38 42 49 39

(a) Test whether the mean productivity is the same for the different machine types.
(b) Test whether the 5 workers differ with respect to mean productivity.
Let us apply coding method. Let us subtract 40 from all the observations.

A B C D
Workers Total X X X X Total
X X X X
1(X 4 -2 7 -4 5 16 4 49 16 85

2 (X ) 6 0 12 3 21 36 0 144 9 189

3(X ) -6 -4 4 -8 -14 36 16 16 64 132

4(X ) 3 -2 6 -7 0 9 4 36 49 98

5(X ) -2 2 9 -1 8 4 4 81 1 90

Total 5 -6 38 -17 20 101 28 326 139 594

H : There is no significant difference in the mean productivity of machine

type.
There is no significant difference in the mean productivity of workers.
H : There is significant difference between in the mean productivity of
machine type.
 There is significant difference between in the mean productivity of
workers.
SST = Sum of squares of all items -

= 594 -

= 594 - = 594 – 20 = 574

∑ ∑ ∑ ∑
SSC =          

=          

=          

=
1794
= - 20 = 358.8-20 = 338.8
5

∑ X1 2 ∑ X2 2 ∑ X3 2 ∑ X4 2 ∑ X5 2 T2
SSR =        
N1 N2 N3 N4 N5 N

52 212 142 02 82 202

=          
4 4 4 4 4 20
25 441 196 64
= - 20
4
726
= - 20
4
= 181.5 – 20
= 161.50

TWO WAY ANOVA TABLE

Source of Sum of Degree of Means square
F - Ratio
Variation Squares freedom
Between SSC= 338.8 c-1= 3 MSC = 338.8 =112.93 112.93
3
Fc = =
Samples 6.142
161.5
18.39
Between SSR=161.5 r-1= 4 MSE = = 40.375
Rows 4
40.375
73.7
Fr = =
Residual SSE= 73.7 (c-1)(r-1)=12 MSE = = 6.142
6.142
12 6.57
Total SST= 574.0 N-1= 19
Between Columns (Machine type)
Calculated value = 18.39
Degree of freedom = (3.12)
Table value of F = 3.49
As the calculated value is greater than the table value, we reject the H0 . Mean
productivity is not the same for different types of machines.

Between rows (workers):

Calculated Value = 6.57
Degree of freedom = (4.12)
Table value of F = 3. 2592
As the calculated value is greater than the table value, we reject the H0
Mean productivity is not the same for different workers.