On Limiting Donor Usage for Imputation of Missing Data via Hot Deck Methods

摘要: Hot deck methods impute missing values within a data matrix by using available from the same matrix. The object which these are taken for imputation is called donor. Selection of suitable donor receiving can be done classes. risk inherent to this strategy that any might selected multiple value recipients. In extreme cases one too many or even all values. To mitigate over usage risk, some hot procedures limit amount times may donation. This study answers if limiting superior when considering variance and bias in parameter estimates.