A general estimation technique of population mean under stratified successive sampling in presence of random scrambled response and non-response

Abstract

This article is an attempt to develop an effective stratified successive sampling estimation procedure which may cope with the problems of simultaneous presence of scrambled response and random non-response in realistic surveys. A generalized class of estimators has been suggested using imputation tool for reducing negative impacts of non-responses in sample surveys. Several estimators are presented as members of the suggested family. We have studied the properties of the suggested strategy and also derived its optimum condition. The dominance of the proposed estimator over the conventional ones has been justified through numerical illustrations carried out over the data set of natural population and population generated through simulation studies using wide varieties of distribution function. Encouraged with the outcomes of the proposed strategy, suitable recommendations to the survey statisticians are also made.

Keywords:

• Successive sampling
• Stratified random sampling
• Scrambled response
• Random non-response
• Imputation
• Simulation study

AMS SUBJECT CLASSIFICATIONS:

• 62D05

Acknowledgements

Authors are thankful to the designated authorities of the Census on Literacy Rates: 2011, India and Statistical Abstract of the United States: 2011 for providing free access on their valuable data set on Internet.

We are also indebted to the reviewers to help us to enhance the quality of the paper markedly and of course to the journal authority to give us the opportunity.