A Forced Odds Ratio (To Be Equal to One) Leads to a New Estimator for Randomized Response Sampling

• Activity Number: 689
• Type: Contributed
• Date/Time: Thursday, August 13, 2015 : 10:30 AM to 12:20 PM
• Sponsor: Survey Research Methods Section
• Author(s): Augustus Jayaraj* and Stephen A. Sedory and Sarjinder Singh and Olusean Odumade
• Companies: and Texas A&M University and Texas A&M University and Deloitte & Touche LLP
• Keywords: Randomized response sampling ; Estimation of proportion ; Mean square error ; Relative efficiency

Abstract

A new estimator for estimating the proportion of a potentially sensitive attribute in survey sampling has been introduced by forcing a constraint of independence of expected responses on the odds ratio. The proposed estimator has been compared to the estimator proposed by Odumade and Singh (2009) with equal protection to all of the respondents. The asymptotic properties of the proposed estimator are investigated through exact numerical illustrations for different choices of parameters. A nonrandomized response approach has been suggested. A scope for further research has also been pointed out.