•  
  •  
 

Abstract

Some imputation techniques are suggested for estimating the population mean when the data values are missing completely at random under a simple random sample without replacement scheme. Two classes of point estimators are proposed. The bias and mean squared error expressions of the proposed point estimators are derived up to first order of approximation. It has been shown that the proposed point estimators are more efficient than some existing point estimators due to Lee, Rancourt, and Sarndal (1994) and Singh and Horn (2000). Theoretical findings are supported by an empirical study based on five populations to show the superiority of the constructed estimators and methods of imputation over others.

Share

COinS