Search

This manuscript considers a dual to product and ratio estimator for estimating the finite population mean of study variable on applying a simple transformation to the auxiliary variable by using its average values in the population that is generally available in practice. The mean square error (MSE) of the proposed estimator has been obtained to the first degree of approximation. The optimum values and range of suitably chosen scalar, under which the proposed estimator perform better, have been determined. A method to lower the MSE of the proposed estimator relative to that of the MSE of the linear regression estimator is developed for small sample sizes. Theoretical and empirical studies have been done to demonstrate the superiority of the proposed estimator over the other estimators. [ABSTRACT FROM AUTHOR]

Improved two phase sampling exponential ratio and product type estimators for population mean using known coefficient of variation of study character in the presence of non response have been proposed and their properties are studied under large sample approximation. The proposed estimators are compared with the other existing estimators by using the MSE criterion and the conditions under which the proposed estimators perform better are obtained. An empirical study is also given to judge the performance of the proposed estimators. At the end, simulation studies have been carried out to verify the superiority to the proposed estimators. [ABSTRACT FROM AUTHOR]

This paper proposes an improved class of ratio-cum-product type exponential estimator for estimating the finite population mean of the study variate (when sampling of study variate is costly or difficult to fetch). The proposed estimator uses two auxiliary variates associated with study variate in order to increase its efficiency under the double sampling for stratification scheme. The expression for the bias and mean square error (MSE) of the proposed estimator are obtained under large sample approximation. Efficiency comparisons are made to demonstrate the performance of the proposed estimation procedure over the existing estimation procedures. We have considered the six natural population data-sets to examine the merits of the proposed estimator and carried out the empirical study in support of theoretical findings. Numerical illustration shows that the proposed estimator is more efficient. [ABSTRACT FROM AUTHOR]