Calibration estimation of population variance under stratified successive sampling in presence of random non response

This paper considers the problem of estimation of population variance of the study character in stratified successive sampling over two occasions under random non-response. Utilizing information available on a highly positively correlated auxiliary variable, a logarithmic type estimator is proposed and its properties, including bias and mean square error, are discussed. Calibration techniques have been applied for determining the optimum strata weight. Empirical studies have been carried out using both real and simulated data to show the efficiency of our proposed estimator over standard estimator, and suitable recommendations have been put forward to the survey statisticians for applications in real life problems.