RBD

Dr. A. Ramesh
DEPARTMENT OF MANAGEMENT
IIT ROORKEE

1
 Learning Objectives

• Estimate variance components in an experiment involving random factors

• Understand the blocking principle and how it is used to isolate the effect
of nuisance factors

• Design and conduct experiments involving the randomized complete block

design

2
 Randomized Block Design

• A completely randomized design (CRD) is useful when the experimental

units are homogeneous

• If the experimental units are heterogeneous, blocking is often used to

form homogeneous groups

3
 Why RBD?

• A problem can arise whenever differences due to extraneous factors (ones

not considered in the experiment) cause the MSE term in this ratio to
become large.
• In such cases, the F value in equation can become small, signaling no
difference among treatment means when in fact such a difference exists.

4
 Randomized block design

• Experimental studies in business often involve experimental units that are

highly heterogeneous; as a result, randomized block designs are often
employed.
• Blocking in experimental design is similar to stratification in sampling.

5
 Randomized block design

• Its purpose is to control some of the extraneous sources of variation by

removing such variation from the MSE term.
• This design tends to provide a better estimate of the true error variance
and leads to a more powerful hypothesis test in terms of the ability to
detect differences among treatment means.

6
 Air Traffic Controller Stress Test
• A study measuring the fatigue and stress of
air traffic controllers resulted in proposals
for modification and redesign of the
controller’s work station
• After consideration of several designs for
the work station, three specific alternatives
are selected as having the best potential
for reducing controller stress
• The key question is: To what extent do the
three alternatives differ in terms of their
effect on controller stress?

7
 Air Traffic Controller Stress Test
• In a completely randomized design, a random sample of controllers would be
assigned to each work station alternative.
• However, controllers are believed to differ substantially in their ability to
handle stressful situations.
• What is high stress to one controller might be only moderate or even low
stress to another.
• Hence, when considering the within-group source of variation (MSE), we must
realize that this variation includes both random error and error due to
individual controller differences.
• In fact, managers expected controller variability to be a major contributor to
the MSE term.

8
 A randomized block design for the air traffic controller
stress test
Treatments
System A System B System C
Controller 1 15 15 18
Controller 2 14 14 14
Controller 3 10 11 15
Blocks
Controller 4 13 12 17
Controller 5 16 13 16
Controller 6 13 13 13

9
Solving this example using ANOVA in python

10
Solving this example using ANOVA in python

11
Summary of stress data for the air traffic controller stress test
Treatments System A System B System C Block total Block
Blocks means
Controller 1 15 15 18 48 x1. =16
Controller 2 14 14 14 42 x2. =14
Controller 3 10 11 15 36 x3. =12
Controller 4 13 12 17 42 x4. =14
Controller 5 16 13 16 45 x5. =15
Controller 6 13 13 13 39 x6. =13
Column Total 81 78 93 252 =
x 252/18
= 14

12
Summary of stress data for the air traffic controller stress test

• Treatment means

x.1 = 81/6 =13.5

x.2 = 78/6 =13
x.3 = 93/6 =15.5

13
ANOVA TABLE FOR THE RANDOMIZED BLOCK DESIGN WITH k
TREATMENTS AND b BLOCKS

Sources of Sum of Degrees of Mean Square F P- value

Variation Squares Freedom

Treatments SS k-1 MS Treatments = MS

Treatments SSTR/k-1 Treatmen
Blocks SS block (b-1) MSBL = SSBL/b- ts / MSE
1
Error SSE (k-1)(b-1) MSE= SSE/(k-
1)(b-1)
Total SST nT-1

14
RBD Problem

15
RBD Problem

16
RBD Problem

17
ANOVA table for the air traffic controller stress test

Sources of Sum of Degrees of Mean Square F P- value

Variation Squares Freedom
Treatments 21 2 10.5 10.5/1.9 0.024
=5.53
Blocks 30 5 6.0
Error 19 10 1.9
Total 70 17

Reject the null hypothesis

18
Solving RBD example using python

19
Solving RBD example using python

20
 Conclusion

• Finally, note that the ANOVA table shown in Table provides an F value to
test for treatment effects but not for blocks.
• The reason is that the experiment was designed to test a single factor—
work station design.
• The blocking based on individual stress differences was conducted to
remove such variation from the MSE term.
• However, the study was not designed to test specifically for individual
differences in stress.

21
 Problem 2: RBD

• An experiment was performed to determine the effect of four different

chemicals on the strength of a fabric.
• These chemicals are used as part of the permanent press finishing
process.
• Five fabric samples were selected, and a randomized complete block
design was run by testing each chemical type once in random order on
each fabric sample.
• The data are shown in Table.
• We will test for differences in means using an ANOVA with alpha = 0.01.

22
 Problem 2: RBD

• Table: Fabric Strength Data—Randomized Complete Block Design

23
Anova using jupyter

24
 Problem 2: RBD

• The sums of squares for the analysis of variance are computed as follows:

25
Problem 2: RBD

26
 Problem 2: RBD
• Analysis of Variance for the Randomized Complete Block Experiment
Sources of Sum of Degrees of Mean F P- value
Variation Squares Freedom Square

Chemical types 18.04 3 6.01 75.13 4.79 E-8

(Treatments)

Fabric samples 6.69 4 1.67

(Blocks)
Error 0.96 12 0.08
Total 25.69 19

27
 Conclusion

• The ANOVA is summarized in the previous table

• Since f0 = 75.13 > f0.01,3,12 = 5.95 (the P-value is 4.79 x E-8), we conclude
that there is a significant difference in the chemical types so far as their
effect on strength is concerned.

28
Python code for problem 2

29
Python code for problem 2

30
Python code for problem 2

31