Estimation of mean using dual-to-ratio and difference-type estimators under measurement error model

TL;DR

This paper develops and compares new dual-to-ratio and difference-type estimators for mean estimation in survey data affected by measurement errors, providing bias and MSE expressions.

Contribution

It introduces novel estimators under measurement error models and derives their bias and mean square error expressions, comparing them with existing estimators.

Findings

Proposed estimators have lower bias and MSE than existing ones.

Derived explicit formulas for bias and MSE under measurement error.

Demonstrated improved estimation accuracy in the presence of measurement errors.

Abstract

In sample survey, when data is collected, it is assumed that whatever is reported by respondent is correct. However, given the issues of prestige bias, personal respect, respondents self reported data often produces over-or-under estimated values from true value. This causes measurement error to be present in sample values. In support of this study, we have considered some precise classes using dual under measurement error model. The expressions for the bias and the mean square errors of proposed classes have been derived and compared with, the mean per unit estimator, the Srivenkataramana 1980 estimator and Sharma and Tailor 2010 estimator.