# Before after with control Group Design

This classical experimental design developed to permit measurement of the effect of the experimental variable alone, may be depicted as follows:

Experimental Group Control Group

Before measurement Yes (x1) Yes (y1)
Experimental variable Yes No
After measurement Yes (x2) Yes (y2)
Effect of experimental variable = (x2 – x1) – (y2 – y1)

The experimental group and the control group are selected in such a way that they are similar, and they are considered interchangeable for test purposes. The control group is measured at the same times as the experimental group, but no experimental variable is introduced. Thus, the difference between the after and before measurements of the control group (y2–y1) is the result of uncontrolled variables. The differences between after and before measurements in the experimental group (x2–x1) is the result of the experimental variables plus the same uncontrolled variables affecting the control group. The effect of the experimental variable alone can be determined by subtracting the difference in the two measurements of the control group from the difference in the two measurements of the experimental group (x2 – x1) – (y2 – y1)

An experiment run by the National Broadcasting Company (NBC) illustrates this design. A carefully selected sample of 2,441 male and female household heads in a medium-sized Midwestern market was interviewed at two different times three months apart. Purchases during the preceding four week period of 22 different brands in 11 different household product categories varying from beer to toothpaste were determined in each of the two interviews. In the first interview the percentage buying one or more of the brands was determined for the entire sample and used as the before measure. In the second interview the sample was separated into two sub-samples – those exposed to 5television and magazine advertising of the products and those not exposed to the advertising.

Purchases by those exposed to advertising during the three month period increased slightly (20.5%-19.4%=1.1%), while purchases by those not exposed to the advertising actually decreased 2.5 percent (16.9%-19.4%). It is assumed that purchases by the experimental group would have also decreased 2.5 percent except for the effect of the advertising. Therefore, it is concluded that the net effect of the advertising was to increase purchasing from 16.9 percent of the household heads to 20.5 percent, a difference of 3.6 percent. This is an 18.6 percent increase in purchases as the results of advertising.

Experimental Group Control Group

Before measurement