Exponential-type estimators of the mean of a sensitive variable in the presence of nonsensitive auxiliary information

Nursel Koyuncu, Sat Gupta, Rita Cristina Pinto de Sousa

Research output: Contribution to journalArticlepeer-review

34 Citations (Scopus)

Abstract

Sousa et al. and Gupta et al. suggested ratio and regression-type estimators of the mean of a sensitive variable using nonsensitive auxiliary variable. This article proposes exponential-type estimators using one and two auxiliary variables to improve the efficiency of mean estimator based on a randomized response technique. The expressions for the mean squared errors (MSEs) and bias, up to first-order approximation, have been obtained. It is shown that the proposed exponential-type estimators are more efficient than the existing estimators. The gain in efficiency over the existing estimators has also been shown with a simulation study and by using real data.

Original languageEnglish
Pages (from-to)1583-1594
Number of pages12
JournalCommunications In Statistics-Simulation And Computation
Volume43
Issue number7
DOIs
Publication statusPublished - 1 Jan 2014

Keywords

  • Absolute relative bias
  • Exponential estimator
  • Mean squared error
  • Randomized response technique
  • Regression estimator

Fingerprint

Dive into the research topics of 'Exponential-type estimators of the mean of a sensitive variable in the presence of nonsensitive auxiliary information'. Together they form a unique fingerprint.

Cite this