![IconGems-Print](images/IconGems-Print.png)
605 – Imputation of Missing Data
A Fresh Imputing Method Using Sensible Constraints on Study and Auxiliary Variables: Preliminary Findings
Choukri Mohamed
Texas A&M University
Sarjinder Singh
Texas A&M University
Stephen A. Sedory
Texas A&M University
In this paper, we propose a new method of imputation for imputing missing values by making use of sensible constraints on a study variable and auxiliary variables which are correlated with the variable of interest. The resultant estimator based on these imputed values is shown to lead to the regression type method of imputation in survey sampling. Further, when the data are missing completely at random (MCAR), the resultant estimator is shown to be a consistent estimator and has asymptotic mean squared error equal to that of the linear regression method of imputation.