Improved Exponential Type Estimators of Finite Population Mean under Complete and Partial Auxiliary Information

Abstract

y Abstract This paper proposes some improved exponential type estimators of fi- nite population mean under simple random sampling and double sam- pling. Expressions for biases and mean squared errors of the proposed estimators are derived up to the first order of approximation. The- oretical and numerical comparisons are made to investigate the per- formances of the estimators. The proposed estimators always perform better than the dierence estimator of the population mean. They also perform better than the estimators suggested by Gupta and Shabbir (3) and Grover and Kaur (2). 2000 AMS Classification: 62D05, 62G05.