Item Sum Double-List Technique: An Enhanced Design for Asking Quantitative Sensitive Questions
Keywords: social desirability, sensitive questions, response bias, item count technique, item sum technique
AbstractSocial desirability bias is a problem in surveys collecting data on sensitive or private topics (e.g. sexual practices, health, income, deviant behavior) as soon as the respondent’s true status differs from a social norm. If confronted with sensitive questions, respondents often engage in self-protective behavior, either by giving socially desirable answers or by refusing to answer at all. Such systematic misreporting or nonresponse leads to biased estimates and poor data quality. To improve the measurement of sensitive topics in population surveys, various indirect questioning techniques have been proposed in the literature. One example, for the measurement of quantitative sensitive characteristics, is the “item sum technique” (IST). In this study we propose an enhanced design for the IST: the “item sum double-list technique” (ISDLT). Compared to the original IST, the ISDLT estimator has a higher statistical efficiency given the same sample size. We first describe our enhanced design, derive prevalence and variance estimators, and show how data collected by the ISDLT can be analyzed. We then provide evidence on the empirical viability of the ISDLT based on a large-scale experimental online survey that asked respondents about their lifetime number of sexual partners and their pornography consumption.
Copyright for articles published in this journal is retained by the authors, with first publication rights granted to the journal. By virtue of their appearance in this open access journal, users can use, reuse and build upon the material published in the journal but only for non-commercial purposes and with proper attribution.