Analyzing Randomized Response Data with a Binomial Selection Procedure

Abstract

The randomized response survey model introduced by Warner (1965) is reviewed and applied to the analysis of contaminated data, i. e., response or reported data which is truthful with probability less than one. Two generic mechanisms are distinguished: an active mechanism whereby the contamination is inserted into the process and hence becomes a statistical design parameter, and a passive mechanism whereby contamination of the response is suspected and hence becomes an analysis parameter. The impact of contamination on the operating characteristics of a subset ranking and selection procedure for binomial models is assessed.