Efficient and alternative approaches for imputing missing data to estimate population mean

Missing data is a routine occurrence in surveys for collecting data. The manuscript presents two novel classes of imputation techniques based on the logarithmic function. Each imputation technique leads to a novel class of point estimator which can be utilized to provide estimates of population mean. Expressions for their bias and mean square errors have been derived. Data has been collected from literature, as well as simulated from three probability distributions to illustrate the performance of the proposed class of estimators when compared with other well-known estimators. Finally, the findings are showcased, and suggestions are put forth for potential real-world implementations.