RAJALAKSHMI INSTITUTE OF TECHNOLOGY

DEPARTMENT OF HUMANITIES AND SCIENCE

I YEAR EVEN SEM – (2021-2022)
ANNA UNIVERSITY QUESTIONS WITH SOLUTION
MA3251 – STATISTICS AND NUMERICAL METHODS
CO2 - UNIT – 2 (DESIGN OF EXPERIMENTS)
PART - A
1. What do you understand by design of an experiment? Explain by examples the need of a design of
experiment to draw sound conclusions.
Ans : The design of an experiment may be defined as the logical construction of the experiment in which
the degree of uncertainty with which the inference is drawn may be well defined.
2. Explain the basic principles of design of experiments. (or) State the principles of Design of Experiments.
Ans : The three basic principals of experimental design are 1. Randomisation, 2. Replication and 3.
Local Control.
3. What is the aim of the design of experiments? Or State the prime objective of design of experiments.
Ans : The prime objective of design of experiments is to control the extraneous variables so that the
results could be attributed only to the experimental variables.
4. What do you mean by replication?
Ans : Replication means ‘the repetition of the treatments under investigation’.
5. What do you mean by Local Control?
Ans : Another way of controlling the effects of extraneous variables is by employing the principle of
local control. It consist of techniques of grouping, blocking and balancing of the experimental units.
Grouping means combining sets of homogenous experimental units into groups so that different groups
may be subjected to different treatments. Each group can have different number of experimental units.
Blocking means assigning the same number of plots or experimental units to different groups, called
blocks. The plots in the same block are relatively similar or homogenous. We may use at random
different manures too different plots in a block.
Balancing means act of equalising effect of the extraneous variable on all the elements in the
experimental group.
6. What is a completely randomized design?
Ans : In a completely randomized design the treatments are given to the experimental units by a
procedure of random allocation. It is used when the units are homogeneous.
7. State the null and alternative hypotheses for a completely randomized design.
Ans : H0 : There is no significance difference between the treatments. H1 : There is significance
difference between the treatments.

PREPARED BY : DEPARTMENT OF H&S (MATHEMATICS) RIT Page 1

 8. What is meant by a randomized block design?
Ans : This design may be defined as one in which the experimental material is divided into blocks are
groups in such way that the units in each block are homogeneous. The treatments are assigned at random
to the units in each block.
9. What is a Latin square design?
Ans : Latin square design controls variation in two directions of the experimental material as rows and
columns resulting in the reduction of experimental error. The analysis of the design results in a
three-way classification of analysis of variance.
10. Is a 2 × 2 Latin square design possible ? Why?
Ans : Consider a 𝑛 × 𝑛 Latin square design, then the degrees if freedom for SSE is equal to (𝑛2 − 1) −
(𝑛 − 1) − (𝑛 − 1) − (𝑛 − 1).(ie) (𝑛 − 1)(𝑛 − 2). For 𝑛 = 2, d.f of SSE is 0 and hence MSE is
not defined. ∴ comparisons are not possible. Hence 2 × 2 Latin square design is not possible.
11. What is the total number of possible Latin squares of order 3?
Ans : Total number of possible Latin squares of order 3 is 12.
In a 3×3 Latin square 3 treatment 𝐴1 , 𝐴2 , 𝐴3 are given with 3 repetitions so that each row and column
receive only one treatment.
In the first row the 3 treatment can be arranged in 3! Ways.
Consider one of these arrangement, say 𝐴1 , 𝐴2 , 𝐴3
In the second row, first place can be filled with 𝐴2 or 𝐴3 , then second and third places will be fixed
automatically. So the second row can be arrange in 2 ways. The third row will be fixed automatically.
Thus all possible arrangements of the treatments = 3! × 2 = 12 ways.
12. Discuss briefly the advantages and disadvantages of CRD.
Ans : Merits :
(i) It has a simple layout.
(ii) There is complete flexibility as the number of replication is not fixed.
(iii)The analysis of the design is simple as it results in a one-way classification analysis of variance.
(iv) Analysis is possible even if some observation are missing.
Demerits :
The experimental error is large as compared to the other designs because homogeneity of the
units is not taken into consideration.
13. Discuss briefly the advantages and disadvantages of RBD.
Ans : Merits :
(i) It has a simple layout but it is more efficient than CRD because of reduction of experimental
error.

PREPARED BY : DEPARTMENT OF H&S (MATHEMATICS) RIT Page 2

 (ii) It is flexible and so any number of treatments and any number of replication may be used.
(iii)The analysis of the design is simple as it results in a two-way classification analysis of variance.
(iv) It is the most popular design with experiments because of its simplicity, flexibility and validity.
Demerits :
(i) If the number of treatments is large, then the size of the blocks will increase this may cause
heterogeneity within blocks.
(ii) The shape of the experimental material should be rectangular.
(iii) If the interactions are large, the experiment may yield misleading results.
14. Discuss briefly the advantages and disadvantages of LSD.
Ans : Merits :
(i) Latin square design controls variation in two directions of the experimental material as rows
and columns resulting in reduction of experimental error.
(ii) The analysis of the design results in a three-way classification of analysis of variance.
(iii) The analysis remains relatively simple even with missing data.
Demerits :
(i) If the number of treatments should be equal to the number of rows and columns as the area
should be in the form of a square.
(ii) The process of randomization is not simple as RBD.
(iii) It is suitable only for a smaller of treatments, say between 5 and 12.
(iv) 2×2 Latin square design is not possible.
15. State the advantages of a factorial experiment over a simple experiment.
Ans : Factorial design is one of the most fruitful advancement in the endeavor to improve the logical
foundations of experimental design. In experiments based on factorial design, the experiment can
evaluate the combined effect of two or more factors when used simultaneously. The factorial design
experiment enables us to study the effect of each and every factor to be estimated and tested
independently by usual analysis of variance.
16. What is the purpose of blocking in a randomized block design?
Ans : If the variation due to heterogeneity in experimental units is so large then the sensitivity of
detecting treatment difference is reduced because of large value of s2. A better idea would be to “block
off” variation due to these units and thus reduce the extraneous variation by smaller homogeneous
blocks.
2
17. Define 2 factorial design.
Ans : Factorial design is one of the most fruitful advancement in the endeavor to improve the logical
foundations of experimental design. In experiments based on factorial design, the experiment can

PREPARED BY : DEPARTMENT OF H&S (MATHEMATICS) RIT Page 3

 evaluate the combined effect of two or more factors when used simultaneously. The factorial design
experiment enables us to study the effect of each and every factor to be estimated and tested
independently by the usual analysis of variance.
18. State the assumptions made while applying ANOVA test. Or What are the basic assumptions in analysis
of variance?
Ans : (i) The samples are drawn from normal populations.
(ii) The variances for the population from which samples have been drawn are equal.
(iii) The variation of each value around its own grant mean should be independent for each value.
19. Define mean square.
Ans : Mean sum of square (MSS). The sum of square divided by its degrees of freedom gives the
corresponding variance or the mean sum of squares (MSS).
20. Write down the format of the ANOVA table for one way classification.
Ans :
Source of variation Sum of squares Degrees of freedom Mean sum of squares Variance ratio
Between samples SSC MSC
SSC or SSR (𝑐 − 1)𝑜𝑟 (𝑟 − 1) MSC = F𝐶 = >1
(columns or row) (𝑐 − 1) MSE

SSE
Residual or error SSE 𝑁−𝑐 MSE =
(𝑁 − 𝑐)
Total TSS 𝑁−1
Where SSC = Sum of squares between samples or columns
SSR = Sum of squares between blocks or rows
SSE = Sum of squares due to error
TSS = Total sum of squares
Variance between samples
F= Variance within samples

21. Write down the format of the ANOVA table for two factors of classification.
Ans :
Source of variation Sum of squares Degrees of freedom Mean sum of squares Variance ratio
SSC MSC
Between samples (columns) SSC (𝑐 − 1) MSC = F𝐶 = >1
(𝑐 − 1) MSE
SSR MSR
Between blocks (rows) SSR (𝑟 − 1) MSR = F𝑅 = >1
(𝑟 − 1) MSE
SSE
Residual or error SSE (𝑟 − 1)(𝑐 − 1) MSE =
(𝑟 − 1)(𝑐 − 1)
Total TSS 𝑁−1

PREPARED BY : DEPARTMENT OF H&S (MATHEMATICS) RIT Page 4

 Where SSC = Sum of squares between samples or columns
SSR = Sum of squares between blocks or rows
SSE = Sum of squares due to error
TSS = Total sum of squares
Variance between samples
F= Variance within samples

22. Write down the format of the ANOVA table for three factors of classification.
Ans :
Source of variation Sum of squares Degrees of freedom Mean sum of squares Variance ratio
SSC MSC
Between samples (columns) SSC (𝑛 − 1) MSC = F𝐶 = >1
(𝑛 − 1) MSE
SSR MSR
Between blocks (rows) SSR (𝑛 − 1) MSR = F𝑅 = >1
(𝑛 − 1) MSE
SSK MSK
Between Letters (treatment) SSK (𝑛 − 1) MSR = F𝐾 = >1
(𝑛 − 1) MSE
SSE
Residual or error SSE (𝑛 − 1)(𝑛 − 2) MSE =
(𝑛 − 1)(𝑛 − 2)
Total TSS 𝑁−1
Where SSC = Sum of squares between samples or columns
SSR = Sum of squares between blocks or rows
SSK = Sum of squares between letters
SSE = Sum of squares due to error
TSS = Total sum of squares
Variance between samples
F= Variance within samples

23. Write any two differences between RBD and LSD. Or Compare and contrast the LSD with RBD.
Ans :
Sl.No LSD RBD
It is suitable for small number of treatments, between 5 and No such restrictions suitable for upto 24
1
12. treatments.
The number of rows and columns are equal and hence, the There is no restriction. It can have any
2
number of replication is equal to the number of treatments. number of replications and treatments.
Experimental error is reduced to a large extent, because Variations is controlled in one direction
3
variation is controlled in two directions. only.
4 Experimental area must be a square. Suitable, if it is a rectangle or square.
24. What are the advantages of completely randomized block design?
25. State the identity for sum of squares for one-way analysis of variance.
26. State 2 difference between completely randomized design and randomized block design.

PREPARED BY : DEPARTMENT OF H&S (MATHEMATICS) RIT Page 5

 PART – B
One Way Classification – Completely Randomized Design (CRD)
1. A company wishes to purchase one of five different machines A, B, C, D, E. In an experiment designed
to decide whether there is a difference in performance of the machines, five experienced operators each
work on the machines for equal times. The following table shows the number of units produced.
A B C D E
68 72 75 42 53
72 52 63 55 48
60 82 65 77 75
48 61 57 64 50
64 65 70 68 53
Test the hypothesis that there is no difference among the machines at (i) 0.05 and (ii) 0.01 level of
significance.
Ans : Null hypothesis H0 : There is no difference among the machines.
Alternative hypothesis H1 : There is a difference among the machines.

𝑋1 𝑋2 𝑋3 𝑋4 𝑋5 𝑋12 𝑋22 𝑋32 𝑋42 𝑋52

68 72 75 42 53 4624 5184 5625 1764 2809
72 52 63 55 48 5184 2704 3969 3025 2304
60 82 65 77 75 3600 6724 4225 5929 5625
48 61 57 64 50 2304 3721 3249 4096 2500
64 65 70 68 53 4096 4225 4900 4624 2809
312 332 330 306 279 19808 22558 21968 19438 16047

N= 25 TSS= 2599.76 MSC=SSC/C-1 92.44

C= 5 SSC= 369.76 MSE=SSE/N-C 111.50
T= 1559 SSE=TSS-SSC 2230.00 F=MSE/MSC 1.21
C.F 97219.24 TABLE VALUE OF F AT 5% & 1% LOS WITH DOF(20,4) ARE 2.87 & 4.43

(OR) USE CODE DATA (EACH DATA SUBTRACTED BY 67)

𝑋1 𝑋2 𝑋3 𝑋4 𝑋5 𝑋12 𝑋22 𝑋32 𝑋42 𝑋52

1 5 8 -25 -14 1 25 64 625 196
5 -15 -4 -12 -19 25 225 16 144 361
-7 15 -2 10 8 49 225 4 100 64
-19 -6 -10 -3 -17 361 36 100 9 289
-3 -2 3 1 -14 9 4 9 1 196
-23 -3 -5 -29 -56 445 515 193 879 1106

N= 25 TSS= 2599.76 MSC=SSC/C-1 92.44

C= 5 SSC= 369.76 MSE=SSE/N-C 111.50
T= -116 SSE=TSS-SSC 2230.00 F=MSE/MSC 1.21
C.F 538.24 TABLE VALUE OF F AT 5% & 1% LOS WITH DOF(20,4) ARE 2.87 & 4.43

PREPARED BY : DEPARTMENT OF H&S (MATHEMATICS) RIT Page 6

 2. The following table shows the lives in hours of four brands of electric lamps.
Brand A 1610 1610 1650 1680 1700 1720 1800
B 1580 1640 1640 1700 1750
C 1460 1550 1600 1620 1640 1660 1740 1820
D 1510 1520 1530 1570 1600 1680
Perform an ANOVA to test the homogeneity of the mean lives of the four brands of lamps.
Ans : Null hypothesis H0 : There is no significance difference between the four brands.
Alternative hypothesis H1 : There is a significance difference between the four brands.

𝑋1 𝑋2 𝑋3 𝑋4 𝑋12 𝑋22 𝑋32 𝑋42

1610 1580 1460 1510 2592100 2496400 2131600 2280100
1610 1640 1550 1520 2592100 2689600 2402500 2310400
1650 1640 1600 1530 2722500 2689600 2560000 2340900
1680 1700 1620 1570 2822400 2890000 2624400 2464900
1700 1750 1640 1600 2890000 3062500 2689600 2560000
1720 1660 1680 2958400 2755600 2822400
1800 1740 3240000 3027600
1820 3312400
11770 8310 13090 9410 19817500 13828100 21503700 14778700

N= 26 TSS= ∑ 𝑥𝑖2 - C.F 195061.54 MSC=SSC/C-1 15075.00

C= 4 2
SSC= (∑ 𝑥𝑖 ) /𝑛𝑖 - C.F 45224.99 MSE=SSE/N-C 6810.75
T=∑ 𝑥𝑖 42580 SSE= TSS-SSC 149836.55 F=MSC/MSE 2.21
2
C.F=𝑇 /𝑁 69732938.46 TABLE VALUE OF F AT 5% LOS WITH DOF(3,22) IS 3.05

ANOVA TABLE
SOURCE OF SUM OF MEAN VARIANCE
D.O.F C.V<T.V
VARIATION SQUARES SQUARE RATIO
BETWEEN
SSC C-1 MSC F=MSC/MSE
COLUMNS IS ACCEPTED
ERROR SSE N-C MSE F>1
TOTAL TSS N-1
(OR) USE CODE DATA (EACH DATA SUBTRACTED BY 1600 AND DIVDED BY 10)
𝑋1 𝑋2 𝑋3 𝑋4 𝑋12 𝑋22 𝑋32 𝑋42
1 -2 -14 -9 1 4 196 81
1 4 -5 -8 1 16 25 64
5 4 0 -7 25 16 0 49
8 10 2 -3 64 100 4 9
10 15 4 0 100 225 16 0
12 6 8 144 36 64
20 14 400 196
22 484

PREPARED BY : DEPARTMENT OF H&S (MATHEMATICS) RIT Page 7

 57 31 29 -19 735 361 957 267

N= 26 TSS= 1950.62 MSC=SSC/C-1 150.75

C= 4 SSC= 452.25 MSE=SSE/N-C 68.11
T= 98 SSE=TSS-SSC 1498.37 F=MSC/MSE 2.21
C.F 369.38 TABLE VALUE OF F AT 5% LOS WITH DOF(3,22) IS 3.05
3. The following are the number of mistakes made in five successive days by 4 technicians working for a
photographic lab.
Technician 1. 6 14 10 8 11
Technician 2. 14 9 12 10 14
Technician 3. 10 12 7 15 11
Technician 4. 9 12 8 10 11
Test whether the differences among the 4 sample means can be attributed to chance.
Hint:
N C T C.F TSS SSC SSE MSC MSE F
20 4 213 2268.45 114.55 12.95 101.60 4.32 6.35 1.47
4. The following table shows the lifetime (in hrs) of samples from three different types of television tubes
manufactured by a company. Test whether there is any difference in the 3 types.
Sample 1. 407 411 409
Sample 2. 404 406 408 405 402
Sample 3. 410 408 406 408
Hint : Coded data is subtract 400 from all the data
N C T C.F TSS SSC SSE MSC MSE F
12 3 84 588.00 72.00 36.00 36.00 18.00 4.00 4.50
5. A company wishes to purchase one of five different machines A, B, C, D, E. In an experiment designed
to decide whether there is a difference in performance of the machines, five experienced operators each
work on the machines for equal times. The following table shows the number of units produced.

A : 68 72 75 42 53
B : 72 52 63 55 48
C : 60 82 65 77 75
D : 48 61 57 64 50
E : 64 65 70 68 53
Test the hypothesis that there is no difference among the machines at
(i) 0.05 and (ii) 0.01 level of significance.
Hint : Coded data is subtract 55 from all the data
N C T C.F TSS SSC SSE MSC MSE F
25 5 184 1354.24 2599.76 756.96 1842.80 189.24 92.14 2.05
6. As part of the investigation of the collapse of the roof of a building, a testing laboratory is given all the
available bolts that connected the steel structure at three different positions on the roof. The forces
required to shear each of these bolts (coded values) are as follows.

PREPARED BY : DEPARTMENT OF H&S (MATHEMATICS) RIT Page 8

 Position 1: 90 82 79 98 83 91
Position 2: 105 89 93 104 89 95 86
Position 3: 83 90 80 94
Perform an analysis of variance to test at the 0.05 level of significance whether the differences among
the sample means at the three positions are significant.
Hint : Coded data is subtract 85 from all the data
N C T C.F TSS SSC SSE MSC MSE F
17 3 86 435.06 936.94 227.64 709.30 113.82 50.66 2.25
7. A completely randomized design experiment with 10 plots and 3 treatments gave the following results. :
Plot no : 1 2 3 4 5 6 7 8 9 10
Treatment : A B C A C C A B A B
Yield : 5 4 3 7 5 1 3 4 1 7

Carry out an ANOVA test.

Hint :
N C T C.F TSS SSC SSE MSC MSE F
10 3 40 160.00 40.00 6.00 34.00 3.00 4.86 1.62
8. The following table gives the yields of 15 samples of plot under three varieties of seed
A 20 21 23 16 20
B 18 20 17 15 25
C 25 28 22 28 32
Test using analysis of variance whether there is a significant difference in the average yield of seeds.
Hint : Coded data is subtract 20 from all the data
N C T C.F TSS SSC SSE MSC MSE F
15 3 30 60.00 330.00 190.00 140.00 95.00 11.67 8.14

PREPARED BY : DEPARTMENT OF H&S (MATHEMATICS) RIT Page 9

 Two Way Classification – Randomized Block Design (RBD)
9. A company appoints 4 salesmen A,B,C and D and observes their sales in 3 seasons: Summer, Winter
and Monsoon. The figures(in lakhs of Rs.) are given in the following table:
Salesmen
Season
A B C D
Summer 45 40 38 37
Winter 43 41 45 38
Monsoon 39 39 41 41
Carry out a two – way analysis of variance.
Ans : USE CODE DATA (EACH DATA SUBTRACTED BY 41)
𝑥1 𝑥2 𝑥3 𝑥4 TOTAL 𝑥12 𝑥22 𝑥32 𝑥42
𝑦1 4 -1 -3 -4 -4 16 1 9 16
𝑦2 2 0 4 -3 3 4 0 16 9
𝑦3 -2 -2 0 0 -4 4 4 0 0
TOTAL 4 -3 1 -7 T = -5 24 5 25 25
Null hypothesis H0 : (i) There is no significance difference between the four salesmen.
(ii) There is no significance difference between the three season.
Alternative hypothesis H1 : (i)There is a significance difference between the four salesmen.
(ii) There is a significance difference between the three season
N=total number of observation=𝑚 × 𝑛=no. of row × no. of column 3×4=12
T=total sum of all the observations=∑ 𝑥𝑖 𝑜𝑟 ∑ 𝑦𝑗 𝑤ℎ𝑒𝑟𝑒 𝑖 =
-5
1 𝑡𝑜 4, 𝑗 = 1 𝑡𝑜 3
C.F=𝑇 2 /𝑁 2.08
TSS=∑ 𝑥𝑖2 - C.F 76.92
SSC=∑(∑ 𝑥𝑖 )2 /𝑛𝑖 - C.F 22.92
2
SSR=∑(∑ 𝑦𝑗 ) /𝑛𝑖 - C.F 8.17
SSE= TSS-SSC-SSR 45.83

ANOVA TABLE

SOURCE OF SUM OF VARIANCE

D.O.F MEAN SQUARE
VARIATION SQUARES RATIO

BETWEEN
SSC=22.92 C-1=3 MSC=SSC/(C-1)=7.64 𝐹𝐶 =MSE/MSC=1
COLUMNS
BETWEEN 𝐹𝑅 =MSE/MSR=1.8
SSR=8.17 R-1=2 MSR=SSR/(R-1)=4.08
ROWS 7
RESIDUAL MSE=SSE/(C-1)(R-1)
SSE=45.83 (C-1)(R-1)=6
OR ERROR =7.64
TOTAL TSS=76.92 N-1=11
Conclusion : (i) The table value of F at 5% of los with dof (6,3) is 8.94 (Column)
PREPARED BY : DEPARTMENT OF H&S (MATHEMATICS) RIT Page 10
 Here C.V<T.V,∴ 𝐻0 𝑖𝑠 𝑎𝑐𝑐𝑒𝑝𝑡𝑒𝑑
(ii) The table value of F at 5% of los with dof (6,2) is 19.33 (Row)
Here C.V<T.V,∴ 𝐻0 𝑖𝑠 𝑎𝑐𝑐𝑒𝑝𝑡𝑒𝑑
(ie) (i) There is no significance difference between the four salesmen.
(ii) There is no significance difference between the three season
10. Perform a 2-way ANOVA on the data given below :-
Treatment 1
1 2 3
1 30 26 38
2 24 29 28
Treatment 2 3 33 24 35
4 36 31 30
5 27 35 33
Use the coding method subtracting 30 from the given number.
Hint :
N C R T C.F SSC SSR SSE MSC MSR MSE F (COLUMN) F (ROW)
ACTUAL
15 3 5 459 14045.4 38.8 52.93 173.87 19.4 13.23 21.73 1.12 1.64
DATA
CODE
15 3 5 9 5.4 38.8 52.93 173.87 19.4 13.23 21.73 1.12 1.64
DATA
11. Three varieties of coal analyzed by 4 chemists and the ash content is tabulated here. Perform an analysis
of variance.
Chemists
Coal
A B C D
I 8 5 5 7
II 7 6 4 4
III 3 6 5 4
Hint :
N C R T C.F TSS SSC SSR SSE MSC MSR MSE F (COLUMN) F (ROW)
12 4 3 64 341.33 24.67 3.33 6.17 15.17 1.11 3.08 2.53 2.28 1.22
12. Yields of four varieties of wheat in 3 blocks are given below:
Blocks
I 10 9 8
II 7 7 6
Varieties
III 8 5 4
IV 5 4 4
Is the difference between varieties and blocks significant?

Hint :
N C R T C.F TSS SSC SSR SSE MSC MSR MSE F (COLUMN) F (ROW)
12 3 4 77 494.08 46.92 8.17 34.92 3.83 4.08 11.64 0.64 6.39 18.22
13. There are three main brands of a certain powder. A set of 120 sample values is examined and found to
be allocated among four groups (A,B,C,D) and three brands (I, II, III) as shown hereunder:
PREPARED BY : DEPARTMENT OF H&S (MATHEMATICS) RIT Page 11
 Groups
Brands
A B C D
I 0 4 8 5
II 5 8 13 6
III 8 19 11 13
Is there any significant difference in brands preference?
Hint :
N C R T C.F TSS SSC SSR SSE MSC MSR MSE F (COLUMN) F (ROW)
12 4 3 100 833.33 280.67 76.67 145.17 58.83 25.56 72.58 9.81 2.61 7.40
14. A company appoints 4 salesmen A,B,C and D and observes their sales in 3 seasons: Summer, Winter
and Monsoon. The figures(in lakhs of Rs.) are given in the following table:

Salesmen
Season
A B C D
Summer 45 40 38 37
Winter 43 41 45 38
Monsoon 39 39 41 41
Carry out a two – way analysis of variance.
Hint : Coded data is subtract 41 from all the data
N C R T C.F TSS SSC SSR SSE MSC MSR MSE F (COLUMN) F (ROW)
12 4 3 -5 2.08 76.92 22.92 8.17 45.83 7.64 4.08 7.64 1.00 1.87
15. From different forms through supposedly equivalent of standardized reading achievement test were
given to each of 5 students and the following are the scores which they obtained:

Student 1 Student 2 Student 3 Student 4 Student 5

Form A: 75 73 59 69 84
Form B: 83 72 56 70 92
Form C: 86 61 53 72 88
Form D: 73 67 62 79 95
Perform a two-way analysis of variance to test at the level of significance 0.01. Whether it is
reasonable to treat the 4 forms as equivalent.
Hint : Coded data is subtract 74 from all the data
N C R T C.F TSS SSC SSR SSE MSC MSR MSE F (COLUMN) F (ROW)
20 5 4 -11 6.05 2708.95 2326.70 42.95 339.30 581.68 14.32 28.28 20.57 1.97
16. The following table gives the yields per acre of four different plant crops grown on lots treated with
three different types of fertilizer. Carry out a two-way ANOVA test at the 0.01 level of significance
whether a) there is a significant difference in yield per acre due to fertilizers
b) there is a significant difference in yield per acre due to crops.

PREPARED BY : DEPARTMENT OF H&S (MATHEMATICS) RIT Page 12

 Crop I Crop II Crop III Crop IV
Fertilizer A 4.5 6.4 7.2 6.7
Fertilizer B 8.8 7.8 9.6 7.0
Fertilizer C 5.9 6.8 5.7 5.2
Hint :
N C R T C.F TSS SSC SSR SSE MSC MSR MSE F (COLUMN) F (ROW)
12 4 3 81.6 554.88 23.08 2.82 13.68 6.58 0.94 6.84 1.10 1.17 6.24
17. Yields of four varieties of wheat in 3 blocks are given below:

Blocks
I 10 9 8
II 7 7 6
Varieties
III 8 5 4
IV 5 4 4
Is the difference between varieties an blocks significant?

Hint : Coded data is subtract from all the data

N C R T C.F TSS SSC SSR SSE MSC MSR MSE F (COLUMN) F (ROW)
12 3 4 77 494.08 46.92 8.17 34.92 3.83 4.08 11.64 0.64 6.39 18.22
18. The following table gives the number of refrigerators sold by 4 salesman in three months.
Salesman
Month A B C D
I 50 40 48 39
II 46 48 50 45
III 39 44 40 39

Is there a significant difference in the sale made by the four salesmen?

Is there a significant difference in the sales made during different month?
Hint : Coded data is subtract 45 from all the data
N C R T C.F TSS SSC SSR SSE MSC MSR MSE F (COLUMN) F (ROW)
12 4 3 -12 12.00 216.00 42.00 91.50 82.50 14.00 45.75 13.75 1.02 3.33
19. The following data represent the number of units of production per day turned out by 5 different workers
using 4 different types of machines:
Machine type
A B C D
1 44 38 47 36
2 46 40 52 43
Workers
3 34 36 44 32
4 43 38 46 33
5 38 42 49 39

PREPARED BY : DEPARTMENT OF H&S (MATHEMATICS) RIT Page 13

 Test whether the five men differ with respect to mean productivity. Test whether the mean productivity
is the same for the four different machine types.
Hint : Coded data is subtract 42 from all the data
N C R T C.F TSS SSC SSR SSE MSC MSR MSE F (COLUMN) F (ROW)
20 4 5 -20 20.00 574.00 338.80 161.50 73.70 112.93 40.38 6.14 18.39 6.57
20. An experiment was designed to study the performance of 4 different detergents for cleaning fuel
injectors. The following cleanness readings were obtained with specially designed equipment for 12
tanks of gas distributed over 3 different models of engines. Perform the ANOVA and test at 0.01 level of
significance whether there are differences in the detergents or in the engines. Table value 𝐹(2,6) =
10.92, 𝐹(3,6) = 9.78

Engine
Detergent
1 2 3
A 45 43 51
B 47 46 52
C 48 50 55
D 42 37 49
Hint : Coded data is subtract 46 from all the data
N C R T C.F TSS SSC SSR SSE MSC MSR MSE F (COLUMN) F (ROW)
12 3 4 13 14.08 264.92 135.17 110.92 18.83 67.58 36.97 3.14 21.53 11.78
21. Three types of indoor lightings: A1, A2 and A3, were tried on three types of flowers : B1,B2 and B3,
grown from a seed. The average heights in cm after 12 weeks of growth are indicated in the following
table.
i) Test, at the 0.05 significance level, whether there is a significant difference in growth due to lighting.
ii) Test, at the 0.05 significance level, whether there is a significant difference in growth due to flower
type.

Flowers
B1 B2 B3
A1 16 24 19
Lighting A2 15 25 18
A3 21 31 15
Hint : Coded data is subtract 23 from all the data
N C R T C.F TSS SSC SSR SSE MSC MSR MSE F (COLUMN) F (ROW)
9 3 3 -23 58.78 232.22 174.22 16.22 41.78 87.11 8.11 10.44 8.34 1.29

PREPARED BY : DEPARTMENT OF H&S (MATHEMATICS) RIT Page 14

 Three Way Classification – Latin Square Design (LSD)
22. Analyze the variance in the Latin square of yields ( in kgs) paddy where P,Q,R,S denote the different
methods of cultivation.
S122 P121 R123 Q122 Examine whether the different methods of cultivation have given significantly
Q124 R123 P122 S125 different yields.
P120 Q119 S120 R121
R122 S123 Q121 P122

Ans :

THREE WAY CLASSIFICATION SQUARES OF

SL.NO I II III IV TOTAL I II III IV
1 122 121 123 122 488 14884 14641 15129 14884
2 124 123 122 125 494 15376 15129 14884 15625
3 120 119 120 121 480 14400 14161 14400 14641
4 122 123 121 122 488 14884 15129 14641 14884
TOTAL 488 486 486 490 1950 59544 59060 59054 60034
SL.NO P Q R S N n T C.F
1 121 122 123 122 16 4 1950 237656
2 122 124 123 125 TSS SSC SSR SSK
3 120 119 121 120 35.75 2.75 24.75 4.25
4 122 121 122 123 SSE MSC MSR MSK
TOTAL 485 486 489 490 4 0.91667 8.25 1.41667
MSE F (COLUMN) F (ROW) F (TREATMENTS)
0.666667 1.375 12.375 2.125
T.V 4.76 4.76 4.76
CONCLUTION ACCEPT NULL HYPOTHESIS
23. The following is a Latin square of a design when 4 varieties of seeds are being tested. Set up an
ANOVA table and state your conclusions.
A 105 B 95 C 125 D 115
C 115 D 125 A 105 B 105
D 115 C 95 B 105 A 115
B 95 A 135 D 95 C 115
Ans : Null hypothesis H0 : There is no significance difference between the column, row and varieties of seeds.
Alternative hypothesis H1 : There is a significance difference between column, row and varieties of seeds.
USE CODE DATA (EACH DATA SUBTRACTED BY 115)
𝑥1 𝑥2 𝑥3 𝑥4 TOTAL 𝑥12 𝑥22 𝑥32 𝑥42
𝑦1 -10 -20 10 0 -20 100 400 100 0
𝑦2 0 10 -10 -10 -10 0 100 100 100
𝑦3 0 -20 -10 0 -30 0 400 100 0
𝑦4 -20 20 -20 0 -20 400 400 400 0
TOTAL -30 -10 -30 -10 -80 500 1300 700 100

PREPARED BY : DEPARTMENT OF H&S (MATHEMATICS) RIT Page 15

 SL.NO A B C D
1 -10 -20 10 0
2 -10 -10 0 10
3 0 -10 -20 0
4 20 -20 0 -20
TOTAL 0 -60 -10 -10

N =𝑛2 Total no. of observations 16

𝑛 No. of column or row 4
Sum of all the observations
𝑛 𝑛
T -80
∑ 𝑥𝑖 (𝑂𝑅) ∑ 𝑦𝑗
𝑖=1 𝑗=1
C.F 𝑇 2⁄ 400.00
𝑁
𝑛

TSS ∑ 𝑥𝑖 2 − C. F 2200.00
𝑖=1
𝑛 2

SSC [(∑ 𝑥𝑖 ) ⁄𝑛] − C. F 100.00

𝑖=1
𝑛 2

SSR [(∑ 𝑦𝐽 ) ⁄𝑛] − C. F 50.00

𝐽=1
SSK [𝑆𝑈𝑀 𝑂𝐹 (𝐴2
, 𝐵 2 , 𝐶 2 , 𝐷2 )⁄𝑛] − C. F 550.00
SSE TSS-SSC-SSR-SSK 1500.00
ANOVA TABLE
SOURCE OF MEAN VARIANCE CALCULATED
SUM OF SQUARES D.O.F CONCLUSION
VARIATION SQUARE RATIO VALUE AT 5%
MSC=
BETWEEN F=MSE/MSC C.V<T.V
SSC=100 𝑛−1=3 SSC/( 𝑛 − 1) F(6,3)=8.94
COLUMNS =7.5 𝐻0 𝑖𝑠 𝑎𝑐𝑐𝑒𝑝𝑡𝑒𝑑
=33.33
MSR=
BETWEEN F=MSE/MSR C.V>T.V
SSR=50 𝑛−1=3 SSR/( 𝑛 − 1) F(6,3)=8.94
ROWS =15 𝐻1 𝑖𝑠 𝑎𝑐𝑐𝑒𝑝𝑡𝑒𝑑
=16.67
MSK=
BETWEEN F=MSE/MSK C.V<T.V
SSK=550 𝑛−1=3 SSK/( 𝑛 − 1) F(6,3)=8.94
LETTERS =1.36 𝐻0 𝑖𝑠 𝑎𝑐𝑐𝑒𝑝𝑡𝑒𝑑
=183.33
MSE=
(𝑛 − 1)(𝑛 SSE/ 𝑛 −
ERROR SSE=1500
− 2) = 6 1)(𝑛 −
2)=250
TOTAL TSS=2200 N-1=15

1.There is no significance difference in seeds from column to column.

2.There is a significance difference in seeds from row to row.
3.There is no significance difference between varieties of seeds.

PREPARED BY : DEPARTMENT OF H&S (MATHEMATICS) RIT Page 16

 24. Analyze the following result by Latin square method.
A 18 C 21 D 25 B 11
D 22 B 12 A 15 C 19
B 15 A 20 C 23 D 24
C 22 D 21 B 10 A 17
Hint : Coded data subtract 18 from all the data

N n T C.F TSS SSC SSR SSK SSE MSC MSR MSK MSE F (COLUMN) F (ROW) F (LETTERS)

16 4 7 3.06 329.94 4.69 29.19 284.19 11.88 1.56 9.73 94.73 1.98 1.27 4.92 47.86
25. An experiment is performed to test the effect on corn field of 4 different fertilizer treatments A, B, C, D
and the soil variations in two perpendicular directions. The following Latin square table is obtained,
where the numbers indicate corn yield per unit area.

C 8 A 10 D 12 B 11
A 14 C 12 B 11 D 15
D 10 B 14 C 16 A 10
B 7 D 16 A 14 C 12
Test at 0.05 level the hypothesis that there is no difference in
a) fertilizers, b) soil variations
Hint : Coded data subtract 12 from all the data

N n T C.F TSS SSC SSR SSK SSE MSC MSR MSK MSE F (COLUMN) F (ROW) F (LETTERS)

4 0 0.00 108.00 30.50 17.50 12.50 47.50 10.17 5.83 4.17 7.92 1.28 1.36 1.90 4
26. Perform an ANOVA on the Latin square of the following table at a 0.05 level

and state conclusions.

Factor 1
B 16 C 21 A 15
Factor 2 A 18 B 23 C 14
C 15 A 18 B 12

Hint : Coded data subtract 18 from all the data

N n T C.F TSS SSC SSR SSK SSE MSC MSR MSK MSE F (COLUMN) F (ROW) F (LETTERS)

9 3 -10 11.11 96.89 74.89 17.56 0.22 4.22 37.44 8.78 0.11 2.11 17.74 4.16 19.00
27. Set up the analysis of variance for the following results of a Latin square design:
A C B D
12 19 10 8
C B D A
18 12 6 7
B D A C
22 10 5 21
D A C B
12 17 27 17
Hint : Coded data subtract 16 from all the data

PREPARED BY : DEPARTMENT OF H&S (MATHEMATICS) RIT Page 17

 N n T C.F TSS SSC SSR SSK SSE MSC MSR MSK MSE F (COLUMN) F (ROW) F (LETTERS)

16 4 -33 68.06 614.94 35.19 127.69 372.69 79.38 11.73 42.56 124.23 13.23 1.13 3.22 9.39
28. Analyze the data given below and interpret the results:
A(13) B (09) C (21) D(07 ) E (06)
D(09) E (08) A(15) B (07 ) C (16)
B(11) C (17 ) D(08) E (10) A(17 )
E (08) A(15) B(07 ) C (10) D(07 )
C (11) D(09) E (08) A(11) B (15)

Hint : Coded data subtract 14 from all the data

N n T C.F TSS SSC SSR SSK SSE MSC MSR MSK MSE F (COLUMN) F (ROW) F (LETTERS)

25 5 -75 225.00 388.00 34.00 26.00 228.40 99.60 8.50 6.50 57.10 8.30 1.02 1.28 6.88
29. Carry out an ANOVA test for the L.S.D:

D B C A
29.1 18.9 29.4 5.7
C A D B
16.4 10.2 21.2 19.1
A D B C
5.4 38.8 24.0 37.0
B C A D
24.9 41.7 9.5 28.9
Hint : Coded data subtract 24 from all the data

N n T C.F TSS SSC SSR SSK SSE MSC MSR MSK MSE F (COLUMN) F (ROW) F (LETTERS)

16 4 -23.8 35.40 1943.08 155.27 259.31 1372.12 156.37 51.76 86.44 457.37 26.06 1.99 3.32 17.55

30. A farmer wishes to test the effects of four different fertilizers A,B,C,D on the yield of wheat. In order to
eliminate sources of error due to variability in soil fertility, he uses the fertilizers in a Latin square
arrangement as indicated in the following table; where the numbers indicate yields in bushels per unit
area.
A C D B
18 21 25 11
D B A C
22 12 15 19
B A C D
15 20 23 24
C D B A
22 21 10 17
Perform an analysis of variance to determine if there is a significant difference between the fertilizers at
= 0.05 levels of significance.
Hint : Coded data subtract 18 from all the data

PREPARED BY : DEPARTMENT OF H&S (MATHEMATICS) RIT Page 18

 N n T C.F TSS SSC SSR SSK SSE MSC MSR MSK MSE F (COLUMN) F (ROW) F (LETTERS)

16 4 7 3.06 329.94 4.69 29.19 284.19 11.88 1.56 9.73 94.73 1.98 1.27 4.92 47.86
31. A variable trial was conducted on wheat with 4 varieties in a Latin square design. The plan of the
experiment and the per plot yield are given below.
C 25 B 23 A 20 D 20
A 19 D 19 C 21 B 18
B1 A 14 D 17 C 20
D 17 C 20 B 21 A 15
Analyse data and interpret the result.
Hint : Coded data subtract 13 from all the data

N n T C.F TSS SSC SSR SSK SSE MSC MSR MSK MSE F (COLUMN) F (ROW) F (LETTERS)

16 4 82 420.25 425.75 41.25 170.25 73.25 141.00 13.75 56.75 24.42 23.50 1.71 2.41 1.04
32. In a Latin square experiment given below are the yields in quintals per acre on the paddy crop carried
out for testing the effect of five fertilizers A, B, C, D, E. Analyse the data for variations.
B 25 A 18 E 27 D 30 C 27
A 19 D 31 C 29 E 26 B 23
C 28 B 22 D 33 A 18 E 27
E 28 C 26 A 20 B 25 D 33
D 32 E 25 B 23 C 28 A 20
Hint : Coded data subtract 25 from all the data

N n T C.F TSS SSC SSR SSK SSE MSC MSR MSK MSE F (COLUMN) F (ROW) F (LETTERS)

25 5 18 12.96 483.04 14.24 3.04 454.64 11.12 3.56 0.76 113.66 0.93 3.84 1.22 122.65

PREPARED BY : DEPARTMENT OF H&S (MATHEMATICS) RIT Page 19

 22 FACTORIAL DESIGN
33. In a processes of growing crystals it is believed that temperature and ph influence yield of crystal, a 22
design is attempted and the following results are obtained for yield.
Temperature Replication
Temperature ph Total
combination I II
(1) 300 2 10 14 24
a 350 2 21 19 40
b 300 3 17 15 32
ab 350 3 20 24 44
(i) Find the mean square error.
[𝐵]
(ii) Verify 𝑦̅.1 − 𝑦̅.0 = 2𝑛
1 1 [𝐴𝐵]
(iii)Verify 2 [𝑦̅11 + 𝑦̅00 ] − 2 [𝑦̅10 + 𝑦̅01 ] = , where 𝑛 is the number of replications.
2𝑛

(iv) Main effects of A and B

(v) Do a complete analysis of the data.
Ans :

PREPARED BY : DEPARTMENT OF H&S (MATHEMATICS) RIT Page 20

PREPARED BY : DEPARTMENT OF H&S (MATHEMATICS) RIT Page 21
PREPARED BY : DEPARTMENT OF H&S (MATHEMATICS) RIT Page 22
 34. Find out the main effects and interactions in the following 22 factorial experiment and write down the
ANOVA table.
1 a b ab
Block
00 10 01 11
I 64 25 30 6
II 75 14 50 33
III 76 12 41 17
IV 75 33 25 10
Ans :

PREPARED BY : DEPARTMENT OF H&S (MATHEMATICS) RIT Page 23

PREPARED BY : DEPARTMENT OF H&S (MATHEMATICS) RIT Page 24
 35. An experiment was planned to study the effect of sulphate of potash and super phosphate on the yield of
potatoes. All the combinations of 2 levels of super phosphate and two levels of sulphate of potash were
studied in a randomized block design with 4 replications for each.The yields (per plot) obtained are
given in the following table.Analyse the data and give your exclusions. Analyse the data and comment
on your finds.(F0.05 (3,9) = 3.86, F0.05 (1,9) = 5.12 ) ).
Block Yields (lb per plot)
(1) K P KP
I
23 25 22 38
P (1) K KP
II
40 26 36 38
(1) K KP P
III
29 20 30 20
KP K P (1)
IV
34 31 24 28

PREPARED BY : DEPARTMENT OF H&S (MATHEMATICS) RIT Page 25