A NEW CLASS OF EXPONENTIAL REGRESSION CUM RATIO ESTIMATOR IN TWO PHASE SAMPLING

Özet

Abstract

In this paper, we propose a new class of exponential regression cumratio estimator using the auxiliary variable for the estimation of thefinite population mean under two phase sampling scheme. The Biasand Mean Square Error (MSE) equations of the proposed estimatorare obtained and compared with the MSE equations of some existingestimators in two phase sampling. We find theoretically the proposedestimator is always more efficient than classical ratio and regression estimators, Singh and Vishwakarma [17] ratio type exponential estimatorin two phase sampling. In addition, theoric results are supported by anumerical example using original data sets.