The relevant variables pose challenges before the investigator because they can influence the dependent variable (the effect), but are of no concern.
So several techniques are used to control them.
Elimination:
- It refers to blocking any chance of occurrence of extraneous variables.
- It is done by creating conditions which are ideal to conduct an experiment.
For example: Conducting the experiment early in the morning to reduce the effect of fatigue as the subject is fresh in the morning.
Matching:
- Elimination is sometime not possible in subjective variables, like interest, motivation, fear etc. or gender, and background factors etc.
In this procedure the relevant variables are equated or are held constant by taking matched pairs across conditions of the experiment.
Example, taking two groups of male from rural background.
Counter-Balancing:
- This is done to eliminate sequence effect.
Instead of giving the task in same order to the group, the order may be interchanged. e.g. AB and BA.
- If the task is to be given to the same individual it can be given in A, B, B, A order.
Constancy:
- When elimination is not possible the variables are kept constant throughout the experiment.
- For example: If noise is being unavoidable, it is kept for the entire experiment, so that its effect remains the same.
Random Assignment:
- This means each and every participant in the study have the chance of being selected in experimental or control group.
- This eliminates any prevailing bias which may affect the study.
For example, if two mixed groups of boys and girls are to be formed, then everyone
should have the chance to be in experimental or control group.