Randomized response

From Wikipedia, the free encyclopedia

Randomized response is a research method used in structured survey interview. It was firstly proposed by S.L. Warner in 1965¹, and later modified by B. G. Greenberg in 1969². It allows respondents to respond to sensitive issues (such as criminal behavior or sexuality) while remaining confidentiality.

It has been used on a number of occasions. For example, social scientists have used it to ask people whether they use drugs, whether they have illegally installed telephones, or whether they have evaded paying taxes. Before abortions were legal, social scientists used the method to ask women whether they had had abortions.

[edit] Example

Ask a man whether he had sex with a prostitute this month. You would ask the question and then ask him to flip a coin. And instruct him to answer "no" if the coin comes up tails and he has not had sex with a prostitute this month. Otherwise, he should answer "yes." Only he knows whether his answer reflects the toss of the coin or his true experience.

Next, look at all the responses in the population. Half the people-or half the questionnaire population-who have not had sex with a prostitute are expected to get tails and the other half are expected to get heads when they flip the coin. For that reason, half of those who have not had sex with a prostitute will answer "yes" even though they have not done it. So whatever proportion of the group said "no," the true number who did not have sex with a prostitute is double that. For example, if 20% of the population surveyed said "no," then the true fraction that did not have sex with a prostitute is 40%.

[edit] References

Note 1: Warner, S. L. (1965). Randomized response: a survey technique for eliminating evasive answer bias. Journal of the American Statistical Association 60, 63--69.

Note 2: Greenberg, B. G., et al. (1969). The Unrelated Question Randomized Response Model: Theoretical Framework. Journal of the American Statistical Association 64(326), 520--539.