ON THE USE OF FAMILIES OF EXPONENTIAL- TYPE ESTIMATORS FOR COMPOSITE IMPUTATION FOR ADJUSTING MISSING DATA

Abstract

The aim of the paper is to suggest some composite methods of imputation (CMI) for filling - in the missing information in the sampled data. These strategies have been developed with the use of an auxiliary variable and with the use of some functions of such a variable in defining some families of exponential type estimators (ETEs). The bias and mean square error of the suggested strategies have been obtained and their particular cases have also been dealt with. A study has been made to compare the performance of all the strategies with each other. Further, in each family of estimators, the optimum estimators have been searched. The results so obtained
have been testified on the basis of some empirical data