Você está na página 1de 10

Completely Randomized Design

• The simplest type of design


• The treatments are assigned completely at random so that each
experimental unit has the same chance of receiving each of the
treatments
• The experimental units are should be processed in random order at all
subsequent stages of the experiment where this order is likely to affect
results
• Any difference among experimental units receiving the same treatment
is considered an experimental error
• Appropriate for experiments with homogenous experimental units
• Appropriate for laboratory and greenhouse experiments
Advantages

• Flexible. Any number of treatments and replicates may be used. The


number of replications may vary (unequal) from treatment to treatment in
order to place more emphasis on treatments of special interest.
• Easy to analyze even if the number of replicates is not the same from
treatment to treatment.
• The method of analysis remains simple even if results of some units are
missing or rejected.
• The relative loss of information due to missing data is smaller than in other
designs
Disadvantages

• Usually suited only for small numbers of treatments and for homogenous
experimental materials

 Large numbers of treatments require relatively large amount of experimental materials


 Large amount of experimental materials tend to increase variation among treatment
responses and thus makes the experimental error large
 This error may be reduced with the use of a different design, unless the units are highly
homogenous or the experimenter has no information by which to arrange or handle the
units in more homogenous groups.

• CRD is seldom used for field experiments because experience has shown
that other designs are more suitable in field conditions
SAMPLE PROBLEM
CRD
The data below represent the number of hours of pain relief provided
by five different brands of headache tablets administered to 25 subjects.
The 25 subjects were randomly divided into five groups and each group
was treated with a different brand.

Brand of Tablet
A B C D E
5 9 3 2 7
4 7 5 3 6
8 8 2 4 9
6 6 3 1 4
3 9 7 4 7
Perform the analysis of variance, and test the hypothesis at the 0.05 l
evel of significance that the mean number of hours of relief provided by
the tablets is the same for all five brands.

• F-test

Source of Degree of Sum of Mean Ftab


Fc
Variation Freedom Squares Squares 5% 1%
Column 4 79.44 19.86 6.90** 2.87 4.43
Error 20 57.60 2.88
TOTAL 24 137.04

** significant at 1% level
Working Equations

cdf = p-1 ; p = no. of columns /group


=5 – 1 = 4
Tdf = pr-1 ; r = no. of subjects / group
= (5)(5) -1
= 24
Edf = Tdf – cdf
= 24 – 4
= 20
Correction Factor, CF

TSS = (52+42+… + 72) – CF= 834 - 696.96


= 137.04
CSS = (262 + 392 + 202 + 142 + 332)/5 – CF
= 776.40 – 696.96
= 79.44
ESS = TSS – CSS
= 137.04 – 79.44
= 57.60
CMS = CSS/Cdf = 79.44/4 = 19.86
EMS = ESS/Edf = 57.60/20 = 2.88
Fc = CMS/EMS
19.86
=
2.88
= 6.90
F (5%, 4,20) = 2.87 = F0.05
F (1%, 4,20) = 4.43 = F0.01
Fc > F0.01
 The 5 brands are significantly different at
1% level of significance
Another Sample Problem: CRD

Very Clean advertises that its detergent will remove all stains, except
oil-based paint, in any kind of water. Consumer Action is evaluating t
his claim. Batches of washing were run in randomly chosen homes h
aving a particular type of water – hard, moderate, or soft. Each batch
contains an assortment of rags and cloth scraps stained with food prod
ucts, grease, and dirt over a 150 square inch area. After washing the n
umber of square inches that were still stained was determines and the
following results were obtained:
Type of Water
Observation
Hard Moderate Soft
1 6 5 5
2 4 6 0
3 3 9 2
4 9 4 4
5 7 3 3

At 5% level, should Consumer Action conclude that the type of wate


r affects the effectiveness of the detergent?

Você também pode gostar