This document discusses various formal research designs used in market research and methodology. It describes the basic principles of formal experimental design including replication, randomization, and local control. It then defines and provides examples of different types of formal designs like completely randomized design, randomized block design, Latin square design, and factorial designs. Factorial designs allow determining the main effects of two or more factors in a single experiment and permit other comparisons of interest. Complex factorial designs are used for experiments with more than two factors.
2. Formal Experimental Design
• Offers more control and use precise statistical procedure.
Basic principles:
o Principle of replication-to provide an estimate of experimental
error.
o Example-Tests done in chemical lab.
o Principle of randomization-to ensure that this estimate is
statistically valid.
o Example- Sales promotion
o Principle of local control-local control, to reduce experimental
error by making the experiment more efficient.
o Example-two way analyses(ANOVA)
4. Formal Completely Randomized Design
Involves 2 principle, principle of Replication and principle of
Randomization.
Uses one way ANOVA
Used in case of homogenous experimental area.
example of whether to provide remedial class to all student or
not on the basis of experiments done on two groups.
Randomization Procedure
-Treatments are assigned to experimental units completely at random.
-Every experimental unit has the same probability of receiving any
treatment.
-Randomization is performed using a random number table, computer
program, etc.
5. Type of Formal Completely Randomized Design
(i)Two-group simple randomized design
7. Randomized block design (R.B. design)
• Addition of local control principle
• Subjects are divided into blocks of homogenous and measurable.
• Each treatment given to be appears the same number of times in
each block.
Example:
8. Latin square design (L.S. design)
• Used in agricultural research
• When there are different major extraneous factors present.
9. Factorial design
• Used in experiments where the effects of varying more than one
factor are to be determined
• important in several economic and social phenomena.
• Factorial designs are used mainly because of the two advantages
– (i) provide equivalent accuracy
• determine the main effects of two (in simple factorial design)
or more (in case of complex factorial design) factors (or
variables) in one single experiment.
– (ii) permit various other comparisons of interest
10. continued
(i) simple factorial designs
we consider effects of two factors on the dependent variable.
two-factor-factorial design.
11. continued
(ii) complex factorial designs
experiments with more than two factors at a time involve the
use of complex factorial design.