On Use of Double Sampling Strategy for the Estimation of Finite Population Mean

The present study attempts to suggest an improved estimator by using two auxiliary variables in estimating the finite population mean. Motivated by Kiregyera and Gupta and Tailor, a regression cum exponential ratio-in-ratio estimator is proposed to estimate the finite population mean under double sampling stratification. Bias and mean squared error expressions are obtained up to the first order of approximation. The performance of the newly proposed estimator is compared theoretically and numerically. The results reveal that the suggested estimator is more efficient and dominates as compared to all competitor estimators. A real data set and simulation study are conducted to verify the performances of estimators.