A MONTE-CARLO ANALYSIS OF MISSING DATA TECHNIQUES IN A HRM SETTING

Researchers have examined various techniques to solve the problem of m issing data. Simple techniques have included listwise deletion, pairwi se deletion, mean substitution, regression imputation and hot-deck imp utation. Past research suggests that regression imputation and pairwis e deletion generally result in less dispersion around true score value s while listwise deletion results in more dispersion around true score s. Unfortunately, this research spent much less lime examining whether the various techniques lead to overestimation or underestimation of t he true values of various statistics. The present study utilized a Mon te Carlo Analysis to simulate an HRM research setting to evaluate miss ing data techniques. Pairwise deletion resulted in the least dispersio n around true scores and least average error of any missing data techn ique for calculating correlations. Implications for use of these techn iques and future missing data research were explored.