Exponential-Ratio-Type Imputation Class of Estimators using Nonconventional Robust Measures of Dispersions

Human-assisted surveys, such as medical and social science surveys, are frequently plagued by non-response or missing observations. Several authors have devised different imputation algorithms to account for missing observations during analyses. Nonetheless, several of these imputation schemes' estimators are based on known auxiliary variable parameters that can be influenced by outliers. In this paper, we suggested new classes of exponential-ratio-type imputation method that uses parameters that are robust against outliers. Using the Taylor series expansion technique, the MSE of the class of estimators presented was derived up to first order approximation. Conditions were also specified for which the new estimators were more efficient than the other estimators studied in the study. The results of numerical examples through simulations revealed that the suggested class of estimators is more efficient.