New Imputation Method for Estimating Population Mean in the Presence of Missing Data

Lack of data due to missing observations may lead to serious issues in statistical analysis. Filling in missing values with possible estimated values using the imputation method could help to eliminate this problem. A new imputation technique has been suggested along with a population mean estimator when missing observations occur in the study. The bias and mean square error of the new estimator are investigated in theory. The performance of the new estimator is examined using applications to air pollution data. The results show that the new imputation method can be used to estimate the population mean leading to minimum mean square error relative to some existing estimators.