A Field Test of Optional Unrelated Question Randomized Response Models: Estimates of Risky Sexual Behaviors
Recently Gupta et al. (Involve J Math, 2013) introduced optional unrelated question randomized response models for both the binary response and quantitative response to sensitive survey questions. Asymptotic normality was established for the mean estimator of the sensitive variable and for the prevalence estimator of the sensitive characteristic. Asymptotic normality was also established for the sensitivity level estimator in each case using first order approximation. These mathematical results were validated using computer simulations. In this paper, the binary and quantitative response models are utilized in surveys of sensitive behaviors to verify that these results hold true in fieldwork applications. The two sensitive questions of interest in the survey are “Have you ever been told by a healthcare professional that you have a sexually transmitted disease?” and “How many sexual partners have you had in the last 12 months?” The target population was undergraduate students enrolled at UNC Greensboro during the 2012–2013 academic year. Subjects were asked these questions by optional unrelated question RRT, check-box survey method, and by direct face-to-face interview. The results of these three methods are compared to each other, as well as to existing published information on these two sensitive behaviors. Estimates provided by the optional unrelated question randomized response models are in line with the mathematical results in Gupta et al. (Involve J Math, 2013). This study also provides the first estimate of sensitivity level through a fieldwork survey.
KeywordsSensitivity Level Sensitive Question Sensitive Behavior Randomize Response Technique Randomization Device
This work was supported by NSF grants DMS 0850465 and DBI 0926288.
- 1.About UNCG: In: Discover UNCG. University of North Carolina at Greensboro. http://admissions.uncg.edu/discover-about.php (2013). Cited 15 Feb 2013
- 5.Department of Health and Human Services: Surveillance summaries. Morb. Mortal. Wkly. Rep. (Centers for Disease Control and Prevention) 58, 1–29 (2009). http://www.cdc.gov/mmwr.Cited15Dec2012
- 7.Dowling, T.A., Shachtman, R.: On the relative efficiency of randomized response models. In: Institute of Statistics Mimeo Series, vol. 811. University of North Carolina, Greensboro (1972)Google Scholar
- 16.Office of Equity, Diversity, and Inclusion: Diversity at UNCG. University of North Carolina at Greensboro. http://oedi.uncg.edu/diversity (2013). Cited 15 Feb 2013
- 19.Stem, D.E., Bozman, C.S.: Respondent anxiety reduction with the randomized response technique. Adv. Consum. Res. 15, 595–599 (1988)Google Scholar