Ratio regression type estimators of the population mean for missing data in sample surveys

In this article, new ratio regression type estimators with imputation have been proposed as means to overcome the problem of missing data relating to a studied variable in a sample survey. It has been shown that the suggested estimators are more efficient than the mean method of imputation, the ratio method of imputation, the regression method of imputation, and the estimators given by Singh and Horn (2000), Singh and Deo (2003), Singh (2009), Diana and Perri (2010) and Gira (2015). The biases and their mean square errors of the suggested estimators are derived. A comparative study is conducted using real and simulated data. The results are found to be encouraging showing improvement of all the methods discussed in this article.