ROHINI COLLEGE OF ENGINEERING AND TECHNOLOGY

2.2 Randomised Block Design (RBD)

Working Rule:
Set the null hypothesis 𝐻0 : There is no significance difference between the treatments.
Step: 1 Find T = The total value of observations
𝑇2
Step: 2 Find the Correction Factor C . F =
𝑁

Step: 3 Calculate the total sum of squares and find the total sum of squares
TSS =(∑ 𝑋1 2 + ∑ 𝑋2 2 + ∑ 𝑋3 2 + . . . ) − 𝐶. 𝐹
(∑ 𝑋1 )2 (∑ 𝑋2 )2 (∑ 𝑋3 )2
Step: 4 Find column sum of squares SSC = ( + + + . . . ) − 𝐶. 𝐹
𝑁1 𝑁2 𝑁3

Where 𝑁𝑖 = Total number of observation in each column (𝑖 = 1, 2, 3, . . . )

(∑ 𝑌1 )2 (∑ 𝑌)2 (∑ 𝑌3 )2
Step: 5 Find Column sum of squares SSR = ( + + + . . . ) − 𝐶. 𝐹
𝑁1 𝑁2 𝑁3

Where 𝑁𝐽 = Total number of observation in each ROW (𝑗 = 1, 2, 3, . . . )

Step: 6 SSE = TSS – (SSC + SSR)
Step: 7 Prepare the ANOVA to calculate F – ratio
Source of Sum of Degrees of Mean Square F - Ratio
variation Degrees Freedom
Between SSC c-1 𝑆𝑆𝐶 𝑀𝑆𝐶
MSC = 𝐹𝑐 =
Columns 𝑐−1 𝑀𝑆𝐸
if MSC> MSE
𝑀𝑆𝐸
𝐹𝑐 =
𝑀𝑆𝐶
if MSE> MSC
Between SSR r–1 MSR =
𝑆𝑆𝐸
𝐹𝑐 =
𝑀𝑆𝑅

Rows 𝑟−1 𝑀𝑆𝐸

if MSR> MSE
𝑀𝑆𝐸
𝐹𝑐 =
𝑀𝑆𝑅
if MSE> MSR
Error SSE (r – 1)(c – 1) MSE =
𝑆𝑆𝐸
(r – 1)(c – 1)

MA3251-STATISTICS AND NUMERICAL METHODS

 ROHINI COLLEGE OF ENGINEERING AND TECHNOLOGY
Step: 8 Find the table value (use chi square table)
Step: 9 Conclusion:
Calculated value < Table value, then we accept null hypothesis.
Calculated value >Table value, then we reject null hypothesis.
PROBLEMS ON TWO WAY ANOVA TABLE
1. Three varieties A, B, C of a crop are tested in a randomized block design with four
replication. The plot yields in pounds as follows.
A6 C5 A8 B9
C8 A4 B6 C9
B7 B6 C10 A6
Analysis the experiment yield and state your conclusion.
Solution:
Set the null hypothesis 𝐻0 : There is no significance difference between the rows and
columns.
VarietiesYields
1 2 3 4 Total
A 6 4 8 6 24
B 7 6 6 9 28
C 8 5 10 9 32
Total 21 15 24 24 84
TEST STATISTIC:
Varieties 1 2 3 4 Total 𝑋1 2 𝑋2 2 𝑋3 2 𝑋4 2
𝑋1 𝑋2 𝑋3 𝑋4
𝑌1 A 6 4 8 6 24 36 16 64 36
𝑌2 B 7 6 6 9 28 49 36 36 81
𝑌3 C 8 5 10 9 32 64 25 100 81
Total 21 15 24 24 84 149 77 200 198

Step:1 Grand Total T = 84

𝑇2 (84)2
Step: 2 Correction Factor C . F = = = 588
𝑁 12

Step: 3 Calculate the total sum of squares and find the total sum of squares
TSS =(∑ 𝑋1 2 + ∑ 𝑋2 2 + ∑ 𝑋3 2 + . . . ) − 𝐶. 𝐹

MA3251-STATISTICS AND NUMERICAL METHODS

 ROHINI COLLEGE OF ENGINEERING AND TECHNOLOGY
=(149 + 77 + 200 + 198) − 588
= 624 − 588 = 36
(∑ 𝑋1 )2 (∑ 𝑋2 )2 (∑ 𝑋3 )2
Step: 4 Find column sum of squares SSC= ( + + + . . . ) − 𝐶. 𝐹
𝑁1 𝑁2 𝑁3

(21)2 (15)2 (24)2 (24)2

SSC = ( + + + ) − 588 = 18
3 3 3 3
(∑ 𝑌1 )2 (∑ 𝑌)2 (∑ 𝑌3 )2
Step: 5 Find Row sum of squares SSR = ( + + + . . . ) − 𝐶. 𝐹
𝑁1 𝑁2 𝑁3

(24)2 (28)2 (32)2

SSR = ( + + + . . . ) − 588 = 8
4 4 4

Step: 6 SSE = Residual sum of squares

= TSS – (SSC + SSR)
= 36 – (18 + 8) 10
Step: 7 Prepare the ANOVA to calculate F – ratio
Source of Sum of Degrees of Mean Square F - Ratio
variation Degrees Freedom
Between SSC=18 c–1 MSC = =
𝑆𝑆𝐶
𝐹𝑐 =
𝑀𝑆𝐶
=3.6
𝑐−1 𝑀𝑆𝐸
Columns = 4 – 1 =3
6
Between SSR=8 r–1 𝑆𝑆𝑅 𝑀𝑆𝑅
MSR = = 𝐹𝑅 = = 2.4
𝑟−1 𝑀𝑆𝐸
Rows =3 – 1 = 2
4
Error SSE = 10 (r – 1)(c – 1) MSE =
2x3=6 𝑆𝑆𝐸
=
(r – 1)(c – 1)
1.667
Step: 8 d.f for (3, 6) at 5% level of significance is 4.76
d.f for (2, 6) at 5% level of significance is 5.14
Step: 9 Conclusion:
Calculated value 𝐹𝑐 < Table value, then we accept null hypothesis.
There is no significance difference between the columns.
Calculated value 𝐹𝑅 < Table value, then we accept null hypothesis.
There is no significance difference between the rows.

MA3251-STATISTICS AND NUMERICAL METHODS

 ROHINI COLLEGE OF ENGINEERING AND TECHNOLOGY
2. Four varieties A, B, C, D of a fertilizer are tested in a randomized block design
with four replication. The plot yields in pounds as follows.
A 12 D 20 C 16 B 10
D 18 A 14 B 11 C 14
B 12 C 15 D 19 A 13
C 16 B 11 A 15 D 20
Analysis the experimental yield.
Solution:
Set the null hypothesis 𝐻0 : There is no significance difference between the rows and
columns.
Varieties Yields
1 2 3 4 Total
A 12 14 15 13 54
B 12 11 11 10 44
C 16 15 16 14 61
D 18 20 19 20 77
Total 58 60 61 57 236 (T)
TEST STATISTIC:
Varieties 1 2 3 4 Total 𝑋1 2 𝑋2 2 𝑋3 2 𝑋4 2
𝑋1 𝑋2 𝑋3 𝑋4
𝑌1 A 12 14 15 13 54 144 196 225 169
𝑌2 B 12 11 11 10 44 144 121 121 100
𝑌3 C 16 15 16 14 61 256 225 256 196
𝑌4 D 18 20 19 20 77 324 400 361 400
Total 58 60 61 57 236 868 942 963 865

Step:1 Grand Total T = 236

𝑇2 (236)2
Step: 2 Correction Factor C . F = = = 3481
𝑁 16

Step: 3 Calculate the total sum of squares and find the total sum of squares
TSS =(∑ 𝑋1 2 + ∑ 𝑋2 2 + ∑ 𝑋3 2 + . . . ) − 𝐶. 𝐹
=(868 + 942 + 963 + 865) − 3481
= 3638 − 3481 = 157
(∑ 𝑋1 )2 (∑ 𝑋2 )2 (∑ 𝑋3 )2
Step: 4 Find column sum of squares SSC= ( + + + . . . ) − 𝐶. 𝐹
𝑁1 𝑁2 𝑁3

MA3251-STATISTICS AND NUMERICAL METHODS

 ROHINI COLLEGE OF ENGINEERING AND TECHNOLOGY
(58)2 (60)2 (61)2 (57)2
SSC = ( + + + ) − 3481
4 4 4 4

= 841 + 900 + 930 + 812 − 3481 = 2

(∑ 𝑌1 )2 (∑ 𝑌)2 (∑ 𝑌3 )2
Step: 5 Find Row sum of squares SSR = ( + + + . . . ) − 𝐶. 𝐹
𝑁1 𝑁2 𝑁3

(54)2 (44)2 (61)2 (77)2

SSR = ( + + + ) − 3481
4 4 4 4

= 729 + 484 + 930.25 + 1482.25 − 3481

= 144.5
Step: 6 SSE = Residual sum of squares
= TSS – (SSC + SSR)
= 157 – (2 +144.5)= 10.5
Step: 7 Prepare the ANOVA to calculate F – ratio
Source of Sum of Degrees of Mean Square F - Ratio
variation Degrees Freedom
Between SSC=2 c–1 MSC =
𝑆𝑆𝐶
𝐹𝑐 =
𝑀𝑆𝐸
=1.74
Columns = 4 – 1 =3 𝑐−1 𝑀𝑆𝐶
=0.666
Between SSR=144.5 r–1 MSR = =
𝑆𝑆𝑅
𝐹𝑅 =
𝑀𝑆𝑅
= 41.51
𝑟−1 𝑀𝑆𝐸
Rows =4 – 1 = 3
48.16
Error SSE = 10.5 (r – 1)(c – 1) MSE =
=3 x 3 = 9 𝑆𝑆𝐸
=
(r – 1)(c – 1)
1.6
Step: 8 d.f for (9, 3) at 5% level of significance is 8.82
d.f for (3, 9) at 5% level of significance is 3.86
Step: 9 Conclusion:
Calculated value 𝐹𝑐 < Table value, then we accept null hypothesis.
There is no significance difference between the columns.
Calculated value 𝐹𝑅 >Table value, then we reject null hypothesis.
There is a significance difference between the rows.

MA3251-STATISTICS AND NUMERICAL METHODS