``Sensitive Survey Questions with Auxiliary Information''

 

  Abstract

Scholars have increasingly relied upon indirect questioning techniques to mitigate social desirability bias and reduce item nonresponse when studying sensitive issues. Their major drawback, however, is the inefficiency of the resulting estimates relative to those based on direct questioning. We show how to improve the statistical analysis of the list experiment (also known as item/unmatched count technique), randomized response technique, and endorsement experiment by exploiting auxiliary information on the sensitive trait of interest. We apply the proposed methodology to survey experiments conducted among voters in a controversial anti-abortion referendum held during the 2011 Mississippi General Election. By incorporating the official county-level election results, we obtain precinct- and individual-level estimates that are more accurate than standard indirect questioning estimates and occasionally even more efficient than direct questioning. Our simulation studies shed light on the conditions under which our approach can improve efficiency and robustness of estimates based on indirect questioning techniques. (Last Revised, October 2016)

  Other Information

See this page for the information about the project on the elicitation of truthful answers to sensitive survey questions. You will find the software that implements the proposed methodologies there too.

© Kosuke Imai
 Last modified: Fri Aug 26 10:54:26 EDT 2016