An improved alternative estimation procedure for current population mean in presence of positively and negatively correlated auxiliary variables in two-occasion rotation patterns

Abstract

The present study confirms the influential role of a positively and a negatively correlated auxiliary variables in enhancing the precision of estimates of current population mean in two occasion rotation (successive) sampling. Exponential-type estimators of current population mean have been proposed for three different situations: (i) the information on a positively correlated auxiliary variable is readily available on both occasions (ii) the information on a negatively correlated auxiliary variable is readily available on both occasions and (iii) the information on both positively and negatively correlated auxiliary variables are readily available on both the occasions. The characteristics of the proposed estimators have been explored and their efficacious performances are compared with the natural and recent contemporary estimators. Optimum replacement strategies of the proposed estimation procedures have been formulated. Simulation and empirical studies are carried out to justify the proposition of the proposed estimators and appropriate recommendations have been put forward to the survey practitioners.

Keywords:

• Exponential-type
• successive sampling
• auxiliary variables
• bias
• mean square error
• optimum replacement strategy
• empirical study

AMS SUBJECT CLASSIFICATION:

• 62D05

Acknowledgments

Authors are thankful to the Editor-in-Chief, Prof. N. Balakrishnan and the reviewer for their valuable suggestions, which helped us in preparing the improved version of the manuscript. Authors are also thankful to the IIT(ISM), Dhanbad, for providing the necessary support to carry out the present research work.