Download as pdf or txt
Download as pdf or txt
You are on page 1of 20

1

ANALYSIS OF VARIANCE
We studied the principles and procedures of testing hypothesis about the equality of
two population means under the assumption that the two random samples are drawn
independently from two normal populations that have equal variance.
However, in many situations we are required to test hypothesis about the equality of
several population means simultaneously. In such cases, one way is to perform two samples t-
tests on all possible pairs of means, but we might be tempted to apply the two sample t-test to
all possible pairwise comparisons of means. For example, if we want to compare 6 population
6 
means, we could perform    15 two sample t-tests. This sort of multiple running two
 2
sample t-tests for comparing means has two disadvantages. First, the procedure is tedious and
time consuming and secondly, the overall significance level greatly increases as the number
of t-tests increases i.e. the more t-tests one runs on a given set of data, the larger the overall
risk of committing type-I error for at least one of the comparisons. For example, if we wish to
10 
test the hypothesis about the equality 10 population means we could perform    45 two
 2
sample t-tests. If the tests are independent and each one is performed using   0.05 , we
could expect 45(0.05)  2.25 such errors even if the null hypothesis H 0 : i   j is true for
each test. Thus a series of two samples t-tests is not an appropriate procedure to test the
equality of several means simultaneously.
Therefore, we require a procedure for carrying out a test of hypothesis about the
equality of several population means simultaneously. For this purpose, Sir Ronald A. Fisher
in 1923 developed a technique called the Analysis of Variance (ANOVA).
The Analysis of Variance is a technique that partitions the total variation present in
the data into its meaningful components, each of which is associated with a different source
of variation. These component parts of variance are then analyzed in such a manner that
certain hypothesis can be tested. This technique is based on the facts that
(i) The more the sample means differ, the larger the variance becomes
(ii) The separate component proved independent and unbiased estimates of the
common population variance.
Therefore the ANOVA procedure compares two different estimates of variance by
using F-distribution to test the equality of the population means. The Analysis of variance is
the most powerful and useful technique whenever the statistical data can be categorized in
groups.
When each observation is classified according to single criterion, we have a one-way
classification while the classification of each observation on the basis of two criteria of
classification simultaneously, is called a two way classification and so on.
2

ONE WAY ANALYSIS OF VARIANCE (ONE WAY ANOVA)


In one way ANOVA the data are classified into k classes, groups or variables of
classification on the basis of a single criterion. The technical term for a class, a group or a
variable of classification is treatment.
Suppose we have k samples of equal size r selected randomly and independently, one
from each of k normal populations with means 1 , 2 ,........, k and common variance  2 .

Samples (Treatments)
Observation
1 2 …….. j …….. k
1 X11 X12 …….. X1j …….. X1k
2 X21 X22 …….. X2j …….. X2k
……

……

……

……

……

……
i Xi1 Xi2 …….. Xij …….. Xik
……

……

……

……

……

……

r Xr1 Xr2 …….. Xrj …….. ……


Xrk Total
Totals T.1 T.2 …….. T.j …….. T.k T..
Means X .1 X .2 …….. X.j …….. X .k X ..

(i) H 0 : 1  2  ........  k
H1 : At least one pair of means differ
(ii) Level of significance:
(iii) Test Statistic:

sb2
F
sw2

Where sb2  Between Mean square

And sw2  Within(error ) Mean square

(iv) Calculation:

T..2
C .F .(Correction factor ) 
n
3

Total S .S .(Total Sum of square)    X ij2  C .F .


i j

 T. 2j
Between samples S .S .( Between samples Sum of square)  j
 C .F .
rj
within or error samples S .S .(Within samples Sumof square)  Total S .S .  Between S .S .

ANOVA table
S.O.V. S.S. M.S.
d.f. F-ratio
(Source of variation) Sum of Square Mean Square

sb2
r   X . j  X ..   SSB
k 2 SSB
Between Samples k 1 s  2
F 2
k 1
b
j 1 sw

   X ij  X . j   SSE
k r 2 SSE
Within (Error) Samples nk sw2  ……
j 1 i 1 nk

   X ij  X ..   SST
k r 2
Total n 1 ------- ……
j 1 i 1

(v) Critical region:


if F  F( , v1 v2
k 1, nk )

Then we shall reject H0


(vi) Conclusion:

…………………………………………………………………………………………………..

Example# 1 Given the data below, test the hypothesis that the means of the three populations
are equal. Let   0.05

Sample 1 Sample 2 Sample 3


40 70 45
50 65 38
60 66 60
65 50 42
Sol:

(i) H 0 : 1  2  3
H1 : At least one pair of means differ
(ii) Level of significance:
  0.05
4

(iii) Test Statistic:

sb2
F
sw2

(iii) Calculation:
Sample 1 Sample 2 Sample 3
40 70 45
50 65 38
60 66 60
65 50 42
T. j 215 251 185 T..  651
T..2 (651)2
C .F .    35316.75
n 12
Total S .S .    X ij2  C .F .
i j

Total S .S .  (40)2  (50)2  (60)2  ..........  (60) 2  (42) 2  35316.75

Total S .S .  36739  35316.75  1422.25

 T. 2j
Between Samples S .S .  j
 C .F .
r
(215)2 (251)2 (185)2
Between Samples S .S .     35316.75
4 4 4
(215)2  (251) 2  (185) 2
Between Samples S .S .   35316.75
4
143451
Between Samples S.S.   35316.75  35862.75  35316.75  546.00
4
within Samples S .S .  Total S .S .  Between S .S .

within Samples S .S .  1422.25  546.00  876.25

ANOVA table
S.O.V. d.f. S.S. M.S. F-ratio

Between 546 sb2 273.00


k 1  3 1  2 546.00 s 
2
 273.00 F 2   2.80
Samples b
2 sw 97.36
Within 876.25
Samples n  k  12  3  9 876.25 sw2   97.36 ……
9
Total n 1  12  1  11 1422.25 ------- ……
5

(v) Critical region:


if F  F( , v1 v2  F(0.05, v1 v2  4.26
k 1, nk ) 2, 9 )

Then we shall reject H0


(vi) Conclusion:
Since the calculated value does not fall in the rejection region, so the null hypothesis
cannot be rejected. It is therefore concluded that means of three populations are equal.
…………………………………………………………………………………………………..

Example# 2 Given the data below, test the hypothesis that the means of the all four
populations are equal. Let   0.05
Sample Number
1 2 3 4
11 13 21 10
4 9 18 4
6 14 15 19
Example# 3 Twenty men are used in an experiment, five being assigned at random to each of
the four machines. The observations are the amount produced by the machines in one day.
Test the hypothesis at   0.05 , that the machines are not different with respect to the
number of items produced.
Machine Number
1 2 3 4
64 41 65 45
39 48 57 51
65 41 76 55
46 49 72 47
63 57 64 47
Example# 4 The following are three consecutive weeks earnings of three salesmen employed
by a given firm.
Salesmen
A B C
152 181 160
175 171 130
180 203 124
Calculate F and assuming that the necessary assumptions can be met, test at 5% level of
significance, whether difference between salesmen are significant.
Example# 5 Determination of yields of a process with four treatments are given. Test the
hypothesis that no differences exist among the four treatments at   0.05 .
6

Treatments
1 2 3 4
11 6 8 14
4 4 6 27
4 3 4 8
5 6 11 18
D.Y.S.
………………………………………………………………………………………………......
Example# 6 Given the data below, test the hypothesis that the means of the three populations
are equal. Let   0.05

Groups Observations
A 4 9 10 11 17 19
B 6 8 10 11 12 12 15
C 9 13 15 20 23
Sol:

(i) H 0 :  A   B  C
H1 : At least one pair of means differ
(ii) Level of significance:
  0.05
(iii) Test Statistic:

sb2
F 2
sw

(iii) Calculation:
Groups
A B C
4 6 9
9 8 13
10 10 15
11 11 20
17 12 23
19 12 ----
--- 15 ----
T. j 70 74 80 T..  224
7

T..2 ( 224)2
C .F .    2787.56
n 18
Total S .S .    X ij2  C .F .
i j

Total S .S .  (4) 2  (9) 2  (10) 2  ..........  (20) 2  (23) 2  2787.56


Total S .S .  3206  2787.56  418.44
 T. 2j
Between groups S .S .  j
 C .F .
rj

(70)2 (74)2 (80)2


Between groups S .S .     2787.56
6 7 5
4900 5476 6400
Between groups S .S .     2787.56
6 7 5
Between groups S .S .  (816.67  782.29  1280)  2787.56
Between groups S .S .  2878.96  2787.56  91.40

within groups S .S .  Total S .S .  Between S .S .

within groups S .S .  418.44  91.40  327.04


ANOVA table
S.O.V. d.f. S.S. M.S. F-ratio

Between 91.40 sb2 45.70


k 1  3 1  2 91.40 sb2   45.70 F   2.10
Groups 2 sw2 21.80
Within 327.04
Groups n  k  18  3  15 327.04 sw2   21.80 ……
15
Total n  1  18  1  17 418.44 ------- ……

(v) Critical region:


if F  F( , v1 v2  F(0.05, v1 v2  3.68
k 1, nk ) 2 , 15 )

Then we shall reject H0


(vi) Conclusion:
Since the calculated value does not fall in the rejection region, so the null hypothesis
cannot be rejected. It is therefore concluded that means of three populations are equal.
…………………………………………………………………………………………………..

Example# 7 Determinations are made on the yield using three methods of catalyzing a
chemical process.
8

Method Measurements
1 47.2 49.8 48.5
2 50.1 49.3 51.5 50.9
3 49.1 53.2 51.2 52.8 52.3
D.Y.S.
………………………………………………………………………………………………......
ASSUMPTIONS OF ONE WAY ANALYSIS OF VARIANCE
(i) The k samples are selected randomly and independently from the k populations.
(ii) All the k populations from which the samples are drawn are normally distributed with
means 1 , 2 ,........., k .
(iii) The normal populations all have equal variances i.e. 12   22  ........   k2   2
(iv) The effects are additive. This means that X ij , the ith observation in the jth samples,
is made up of three component quantities as follows;
X ij     j   ij
Where  is the overall mean,  j is the sample or treatment effect for jth
population and  ij is the random error, usually considered a normally and
independently distributed variable with zero mean and common variance  2 .
…………………………………………………………………………………………………..
TWO WAY ANALYSIS OF VARIANCE (TWO WAY ANOVA)
When each observation is classified according to two criteria (or variables) of
classification simultaneously, we use the two way Analysis of Variance technique. The
classified data are recorded in a table, in which the columns represent one criterion (or
variable) of the classification and the rows represent the other criterion. If there are c columns
and r rows in the table, then there will be altogether rc cells. Each cell may contain a single
observation or several observations.
There are two basic forms of two way analysis of variance, depending upon whether
the two variables of classification are independent or whether they interact.
TWO WAY ANALYSIS OF VARIANCE (Without Interaction)
Let X ij denote an observation in the ith row and jth column in a table consisting of r
rows and c columns and containing sample data from normal populations with means ij and
the common variance  2 , classified according to two criteria of classification simultaneously.
9

Columns
Rows Total Means
1 2 …….. j …….. c
1 X11 X12 …….. X1j …….. X1c T1. X 1.

2 X21 X22 …….. X2j …….. X2c T2. X 2.


……

……

……

……

……

……

……

……
i Xi1 Xi2 …….. Xij …….. Xic Ti . Xi.
……

……

……

……

……

……

……

……

……
r Xr1 Xr2 …….. Xrj …….. Xrc Tr . X r.

Totals T.1 T.2 …….. T.j …….. T.c T.. X ..

Means X .1 X .2 …….. X.j …….. X .c X ..

(i) H 0 : All row ' s means are equal


H 0 : All column ' s means are equal
H1 : At least one pair of row ' s means differ
H1: At least one pair of columns ' s means differ
OR

H 0 : 1.  2.  .......  r .


H 0 : .1  .2  .......  .c
H1 : At least one pair of i . differ
H1: At least one pair of . j differ
(ii) Level of significance:
(iii) Test Statistic:
sr2
F1 
se2

sc2
F2  2
se
Where sr2  Rows Mean Square

sc2  Columns Mean Square


10

se2  Error Mean Square


(iv) Calculation:
T..2
C .F . 
n
r c
Total S .S .    X ij2  C .F .
i 1 j 1

r
 Ti .2
Between Rows S .S .  i 1  C .F .
c
c
 T. 2j
j 1
Between Columns S .S .   C .F .
r
Error S .S .  Total S .S .  Between Rows S .S .  BetweenColumns S .S .
ANOVA table
S.O.V. d.f. S.S. M.S. F-ratio
sr2
c   X i .  X ..   SSR
r SSR
F1 
2
Between Rows r 1 sr2 
i 1 r 1 se2
sc2
r   X . j  X ..   SSC
c 2 SSC
Between Columns c 1 sc2  F2 
j 1 c 1 se2
SSE
Error ( r  1)(c  1) SSE se2  ……
(r  1)(c  1)

   X ij  X ..   SST
r c 2
Total n 1 ------- ……
i 1 j 1

(v) Critical region:

if F1  F( , v1 v2
r 1, ( r 1)( c1) )

Then we shall reject H 0

And if F2  F( , v1 v2
c1, ( r 1)( c1) )

Then we shall reject H 0

(vi) Conclusion:

…………………………………………………………………………………………………..

Example# 20.5 (page# 316)


(i) H 0 : All observer ' s means are equal
H 0 : All consignment ' s means are equal
11

H1 : At least one pair of observer ' s means differ


H1: At least one pair of consignment ' s means differ
OR
H 0 : 1.  2.  3.  4.
H 0 : .1  .2  .3  .4  .5  .6
H1 : At least one pair of i . differ
H1: At least one pair of . j differ
(ii) Level of significance:
  0.05
(iii) Test Statistic:

sr2
F1 
se2

sc2
F2 
se2

P.T.O.

(iv) Calculation:
Consignments
Observers Ti . Ti .2
1 2 3 4 5 6
1 9 10 9 10 11 11 60 3600
2 12 11 9 11 10 10 63 3969
3 11 10 10 12 11 10 64 4096
4 12 13 11 14 12 10 72 5184

T. j 44 44 39 47 44 41 T.. = 259  Ti .2  16849


i 1

T. 2j 1936 1936 1521 2209 1936 1681  T. 2j  11219


j 1
12

T..2 ( 259)2
C .F .    2795.04
n 24
r c
Total S .S .    X ij2  C .F .
i 1 j 1

Total S .S .  (9)2  (10)2  (9)2  ........  (12)2  (10)2  2795.04

Total S .S .  2831  2795.04  35.96


r
 Ti .2
Between observers S .S .  i 1  C .F .
c
16849
Between observers S .S .   2795.04
6
Between observers S .S .  2808.17  2795.04  13.13
c
 T. 2j
j 1
Between consignments S .S .   C .F .
r
11219
Between consignments S .S .   2795.04
4
Between consignments S .S .  2804.75  2795.04  9.71

Error S .S .  Total S .S .  Between observers S .S .  Between consginments S .S .

Error S .S .  35.96  13.13  9.17

Error S .S .  13.12

ANOVA table
S.O.V. d.f. S.S. M.S. F-ratio

Between 13.13 sr2 4.38


r 1  4 1  3 13.13 sr2   4.38 F1    5.03
Observers 3 se2 0.87

Between 9.71 sc2 1.94


c 1  6 1  5 9.71 sc2   1.94 F2    2.23
Consignments 5 se2 0.87
13.12
Error ( r  1)(c  1)  3  5  15 13.12 se2   0.87 ……
15
Total n  1  24  1  23 35.96 ------- ……

(v) Critical region:


13

if F1  F( , v1 v2  F( , v1 v2  3.29


r 1, ( r 1)( c1) ) 3 , 15 )

Then we shall reject H 0

And if F2  F( , v1 v2  F( , v1 v2  2.90


c1, ( r 1)( c1) ) 5 , 15 )

Then we shall reject H 0

(vi) Conclusion:

Since the computed value of F1  5.03 falls in the rejection region, therefore the null
hypothesis H 0 rejected. It is therefore concluded that At least one pair of observer’s
means differ significantly.

Since the computed value of F2  2.23 does not fall in the rejection region, therefore
the null hypothesis H 0 cannot be rejected. It is therefore concluded that there is no
significant difference between the means of consignments.

…………………………………………………………………………………………………..

Q# 20.19, 20.20, 20.21 (a) (b), 20.22, 20.23, 20.24, 20.25


D.Y.S.
…………………………………………………………………………………………………..
PARTITIONING THE SUM OF SQUARES FOR TWO WAY ANOVA

Total S . S .     X ij  X .. 
r c 2

i 1 j 1

By adding and subtracting X i . , X . j and X .. on right hand side

Total S . S .     X ij  X i .  X i .  X . j  X . j  X ..  X ..  X .. 
r c 2

i 1 j 1

Total S . S .     X i .  X ..    X . j  X ..    X ij  X i .  X . j  X .. 


r c 2

i 1 j 1

Total S . S .     X i .  X ..      X . j  X ..      X ij  X i .  X . j  X .. 
r c 2 r c 2 r c 2

i 1 j 1 i 1 j 1 i 1 j 1

 three Cross  product terms , which will be vanished

Total S . S .  c   X i .  X ..   r   X . j  X ..      X ij  X i .  X . j  X .. 
r 2 c 2 r c 2

i 1 j 1 i 1 j 1

Total S . S .  Between Rows S . S .  Between Columns S . S .  Error S . S .

With d.f.
n  1  (r  1)  (c  1)  ( r  1)(c  1)

………………………………………………………………………………………………
14

MULTIPLE COMPARISON TESTS


If the null hypothesis rejects after applying the F-test in ANOVA , then one conclude
that At least one pair of means differ. This conclusion might not be sufficient to satisfy the
experimenter; rather he would like to know which means might differ significantly from each
other. For this purpose, we will use the following multiple comparison tests to compare the
pairs of means.

(i) The Least Significant Difference Test (LSD Test)


(ii) The Duncan’s Multiple Range Test.

(i) THE LEAST SIGNIFICANT DIFFERENCE TEST (LSD TEST)


When the null hypothesis of equal means is rejected by F-test after the ANOVA, we
can test the significance of differences between means of k samples by using the ordinary two
sample t-test on every possible pairs of X i and X j (i  j ) at significance level  . But this
procedure involves a large number of decisions. An alternative method of dealing such a
situation is to compute the smallest difference with which absolute values of all the
differences of means are to be compared.
This smallest difference is called the least significant difference or LSD and is given
by;
2( MSE )
LSD  t 
( , error of d . f .)
2
r
Where MSE is the error mean square, r is the size of equal samples. The test criterion
that uses the least significant difference is called the LSD test.
Two means are declared to be significantly different, if the absolute value of their
difference exceeds the LSD.
…………………………………………………………………………………………………..

Example# 20.7 (page# 325)


(i) H 0 : All treatment ' s means are equal
H1 : At least one pair of treatment ' s means differ
(ii) Level of significance:
  0.05
(iii) Test Statistic:

sr2
F1 
se2

sc2
F2 
se2
15

(iv) Calculation:
Treatments
Blocks Ti . Ti .2
1 2 3 4 5 6
1 1 3 6 4 3 2 19 361
2 1 4 4 8 5 1 23 529
3 3 6 7 8 4 3 31 961
4 2 3 2 3 2 1 13 169

T. j 7 16 19 23 14 7 T.. = 86  Ti .2  2020
i 1

T. 2j 49 256 361 529 196 49  T. 2j  1440


j 1

7
X.j  1.75 4.00 4.75 5.75 3.50 1.75
4

T..2 (86)2
C .F .    308.17
n 24
r c
Total S .S .    X ij2  C .F .
i 1 j 1

Total S .S .  (1)2  (1)2  (3)2  ........  (3)2  (1)2  308.17

Total S .S .  412  308.17  103.83


r
 Ti .2
Between Blocks S .S .  i 1  C .F .
c
2020
Between Blocks S .S .   308.17  28.50
6
c
 T. 2j
j 1
Between treatments S .S .   C .F .
r
1440
Between treatments S .S .   308.17  51.83
4
Error S .S .  Total S .S .  Between Blocks S .S .  Between Treatments S .S .

Error S .S .  103.83  28.50  51.83  23.50

ANOVA table
S.O.V. d.f. S.S. M.S. F-ratio
Between 28.50
Blocks r 1  4 1  3 28.50 sr2   9.50 ……
3
16

Between 51.83 sc2 10.37


c 1  6 1  5 51.83 sc2   10.37 F2    6.61
Treatments 5 se2 1.57
23.50
Error ( r  1)(c  1)  3  5  15 23.50 se2   1.57 ……
15
Total n  1  24  1  23 103.83 ------- ……

(v) Critical region:

if F2  F( , v1 v2  F( , v1 v2  2.90


c1, ( r 1)( c1) ) 5 , 15 )

Then we shall reject H 0

(vi) Conclusion:

Since the computed value of F2  6.61 falls in the rejection region, therefore the null
hypothesis rejected. It is therefore concluded that At least one pair of treatment’s means
differ significantly.

Because H 0 is rejected using F-test, therefore we apply the LSD test to find which
pairs of means differ significantly as;

2( MSE )
LSD  t 
( , error of d . f .)
2
r

2(1.57)
LSD  t( 0.025, 15)
4

2(1.57)
LSD  ( 2.13)  1.89
4

Arranging the treatment means in ascending order of magnitude, we get

x1 x6 x5 x2 x3 x4
1.75 1.75 3.50 4.00 4.75 5.75

Comparison Absolute Differences Conclusion


4 vs. 1 5.75 – 1.75 = 4.00 > LSD Significant
4 vs. 6 5.75 – 1.75 = 4.00 > LSD Significant
4 vs. 5 5.75 – 3.50 = 2.25 > LSD Significant
4 vs. 2 5.75 – 4.00 = 1.75 < LSD Insignificant
4 vs. 3 5.75 – 4.75 = 1.00 < LSD Insignificant
3 vs. 1 4.75 – 1.75 = 3.00 > LSD Significant
17

3 vs. 6 4.75 – 1.75 = 3.00 > LSD Significant


3 vs. 5 4.75 – 3.50 = 1.25 < LSD Insignificant
3 vs. 2 4.75 – 4.00 = 0.75 < LSD Insignificant
2 vs. 1 4.00 – 1.75 = 2.25 > LSD Significant
2 vs. 6 4.00 – 1.75 = 2.25 > LSD Significant
2 vs. 5 4.00 – 3.50 = 0.50 < LSD Insignificant
5 vs. 1 3.50 – 1.75 = 1.75 < LSD Insignificant
5 vs. 6 3.50 – 1.75 = 1.75 < LSD Insignificant
6 vs. 1 1.75 – 1.75 = 0.00 < LSD Insignificant

Alternative Method
Arranging the treatment means in ascending order of magnitude and drawing a line
under the pair of adjacent means that are not significantly different, we have;
x1 x6 x5 x2 x3 x4
1.75 1.75 3.50 4.00 4.75 5.75

…………………………………………………………………………………………………..
Q# 20.31 (b) D.Y.S.
…………………………………………………………………………………………………..
(ii) THE DUNCAN’S MULTIPLE RANGE TEST

MSE
; Rp  q ( p, error d . f .)
p  2,3,..., k  1, k
r
…………………………………………………………………………………………………..
Example# 20.8 (page# 328)
(i) H 0 : All treatment ' s means are equal
H1 : At least one pair of treatment ' s means differ
(ii) Level of significance:
  0.05
(iii) Test Statistic:

sr2
F1 
se2

sc2
F2 
se2
18

(iv) Calculation:
Treatments
Blocks Ti . Ti .2
1 2 3 4 5 6
1 1 3 6 4 3 2 19 361
2 1 4 4 8 5 1 23 529
3 3 6 7 8 4 3 31 961
4 2 3 2 3 2 1 13 169

T. j 7 16 19 23 14 7 T.. = 86  Ti .2  2020
i 1

T. 2j 49 256 361 529 196 49  T. 2j  1440


j 1

7
X.j  1.75 4.00 4.75 5.75 3.50 1.75
4

T..2 (86)2
C .F .    308.17
n 24
r c
Total S .S .    X ij2  C .F .
i 1 j 1

Total S .S .  (1)2  (1)2  (3)2  ........  (3)2  (1)2  308.17

Total S .S .  412  308.17  103.83


r
 Ti .2
Between Blocks S .S .  i 1  C .F .
c
2020
Between Blocks S .S .   308.17  28.50
6
c
 T. 2j
j 1
Between treatments S .S .   C .F .
r
1440
Between treatments S .S .   308.17  51.83
4
Error S .S .  Total S .S .  Between Blocks S .S .  Between Treatments S .S .

Error S .S .  103.83  28.50  51.83  23.50

ANOVA table
S.O.V. d.f. S.S. M.S. F-ratio
Between 28.50
Blocks r 1  4 1  3 28.50 sr2   9.50
3
19

Between 51.83 sc2 10.37


c 1  6 1  5 51.83 sc2   10.37 F2    6.61
Treatments 5 se2 1.57
23.50
Error ( r  1)(c  1)  3  5  15 23.50 se2   1.57 ……
15
Total n  1  24  1  23 103.83 ------- ……

(v) Critical region:

if F2  F( , v1 v2  F( , v1 v2  2.90


c1, ( r 1)( c1) ) 5 , 15 )

Then we shall reject H 0

(vi) Conclusion:

Since the computed value of F2  6.61 falls in the rejection region, therefore the null
hypothesis rejected. It is therefore concluded that At least one pair of treatment’s means
differ significantly.

Because H 0 is rejected using F-test, therefore we apply the Duncan’s Multiple Range
test to find which pairs of means differ significantly as;

MSE
Rp  q ( p, error d . f .) ; p  2,3, 4,5,6
r

1.57
Rp  q0.05 ( p, 15)
4
Rp  q0.05 ( p, 15) (0.6265)
Arranging the treatment means in ascending order of magnitude, we get

x1 x6 x5 x2 x3 x4
1.75 1.75 3.50 4.00 4.75 5.75

p q0.05 ( p, 15) Rp  q0.05 ( p, 15) (0.6265)


2 q0.05 (2, 15)  3.01 3.01 0.6265  1.89 ( R2 )
3 q0.05 (3, 15)  3.16 1.98 ( R3 )
4 q0.05 (4, 15)  3.25 2.04 ( R4 )
5 q0.05 (5, 15)  3.31 2.07 ( R5 )
6 q0.05 (6, 15)  3.36 2.11 ( R6 )

Comparison Absolute Differences Conclusion


20

4 vs. 1 5.75 – 1.75 = 4.00 > 2.11 ( R6 ) Significant


4 vs. 6 5.75 – 1.75 = 4.00 > 2.07 ( R5 ) Significant
4 vs. 5 5.75 – 3.50 = 2.25 > 2.04 ( R4 ) Significant
4 vs. 2 5.75 – 4.00 = 1.75 < 1.98 ( R3 ) Insignificant
4 vs. 3 5.75 – 4.75 = 1.00 < 1.89 ( R2 ) Insignificant
3 vs. 1 4.75 – 1.75 = 3.00 > 2.07 ( R5 ) Significant
3 vs. 6 4.75 – 1.75 = 3.00 > 2.04 ( R4 ) Significant
3 vs. 5 4.75 – 3.50 = 1.25 < 1.98 ( R3 ) Insignificant
3 vs. 2 4.75 – 4.00 = 0.75 < 1.89 ( R2 ) Insignificant
2 vs. 1 4.00 – 1.75 = 2.25 > 2.04 ( R4 ) Significant
2 vs. 6 4.00 – 1.75 = 2.25 > 1.98 ( R3 ) Significant
2 vs. 5 4.00 – 3.50 = 0.50 < 1.89 ( R2 ) Insignificant
5 vs. 1 3.50 – 1.75 = 1.75 < 1.98 ( R3 ) Insignificant
5 vs. 6 3.50 – 1.75 = 1.75 < 1.89 ( R2 ) Insignificant
6 vs. 1 1.75 – 1.75 = 0.00 < 1.89 ( R2 ) Insignificant
………………………………………………………………………………………………
Q# 20.30 (a) (b)
………………………………………………………………………………………………...

You might also like