Hybrid of Crossed Model and a New Unrelated Question Model for Two Sensitive Characteristics

• Activity Number: 476 - Innovations in Analytic Approaches for Survey Data
• Type: Contributed
• Date/Time: Thursday, August 6, 2020 : 10:00 AM to 2:00 PM
• Sponsor: Survey Research Methods Section
• Author(s): Stephen Sedory* and Renhua Zheng and Sarjinder Singh
• Companies: Texas A&M University-Kingsville and Texas A&M University-Kingsville and Texas A&M Kingsville
• Keywords: randomized response; estimation of proportions; unrelated question model

Abstract

In this paper we address the estimation of a number of parameters associated with the proportions of a population possessing two sensitive characteristics. Our estimators are derived from a hybrid of two other estimators, one, the crossed model introduced by Lee et al. in 2013, and the other, a newly created unrelated-question model. We review the first model, introduce the second model, derive some of its features and then propose the hybrid model as a fix for certain of its deficiencies. Finally we look at how the performance of the estimators varies with the particular parameter being estimated.