An Improved Generalized Difference-Cum-Ratio-Type Estimator for the Population Variance in Two-Phase Sampling Using Two Auxiliary Variables

Abstract

In this paper, an improved generalized difference-cum-ratio-type estimator for the finite population variance under two-phase sampling design is proposed. The expressions for bias and mean square error (MSE) are derived to first order of approximation. The proposed estimator is more efficient than the usual sample variance estimator, traditional ratio estimator, traditional regression estimator, chain ratio type and chain ratio-product-type estimators, and Jhajj and Walia (2011) estimator. Four datasets are also used to illustrate the performances of different estimators.

Keywords:

• Auxiliary variables
• Bias
• Efficiency
• MSE
• Two-phase sampling

Mathematical Subject Classification:

• 62D05

Acknowledgments

The authors are thankful to the learned referees for their valuable suggestions that helped improve the manuscript.