Research
Exponential Estimators of Population Mean in Post-Stratified Sampling using Known Value of Some Population Parameters
This paper proposes some exponential estimators of the population mean in post-stratified sampling (PSS) scheme, when using known value of some population parameters. The bias and mean squared error of the proposed estimators are obtained up to first order approximations. Conditions under-which the proposed estimators perform better than other estimators, like the post-stratified sampling mean estimator, the ratio type estimator and the dual to ratio estimator, proposed by Onyeka (2012, 2013), are obtained. The theoretical results are further verified and confirmed using numerical illustrations.
Estimation of Population Ratio in Simple Random Sampling using Variable Transformation
This paper proposes six new estimators of the population ratio (R) of the population means of two variables (y and x) in Simple Random Sampling (SRS) scheme, using a variable transformation of the auxiliary variable, x. Properties of the proposed estimators, including optimality conditions, are derived up to first order approximation, and conditions under which the proposed estimators perform better than the customary ratio estimator ( ) are also obtained. The results are supported with empirical illustrations, which show that some of the proposed estimators have relatively large gains in efficiency over the customary ratio estimator, for the data set considered.
Dual to Ratio Estimators of Population Mean in Post-Stratified Sampling using Known Value of Some Population Parameters
This paper extends the work carried out by Onyeka (2012), by proposing a class of dual to ratio combined estimators of the population mean in post-stratified sampling when using known value of some population parameters. The proposed estimators, under certain conditions, are shown to be more efficient than some existing estimators, including the usual poststratified estimator and the estimators proposed by Onyeka (2012). Properties of the proposed class of estimators, including conditions for optimal efficiency, are obtained up to first order approximation. The results are illustrated using empirical data.
