Manipulation check

Manipulation check is a term in experimental research in the social sciences which refers to certain kinds of secondary evaluations of an experiment. Manipulation checks get at the interpretation of participants of factors in an experimental setting.

For a hypothetical example, consider a psychological study of determinants of happiness with a restaurant meal, in which subjects are each given one of two restaurant situation scenarios to read, and then asked to evaluate how happy they would be in that situation on a 1-7 Likert scale. The two versions of scenario differ in only one way, what color is stated to be the decor of the restaurant. Suppose that the subjects in the red decor option give ratings that are statistically significantly higher than those with the blue decor option. One would tend to conclude that restaurant decor color matters. But, a manipulation check could be to ask the subjects, after giving their rating, what was the color of the restaurant decor, to see if they could recall it. If they do not remember, that tends to suggest that the subjects did not attend to that detail in the scenario, that it did not matter to them. Then, it should be interpreted that the difference in overall results is less likely to be caused by the color difference, and it is more likely to be the result of random variation.

See also