Chained equations and more in multiple imputation in Stata 12

This session focuses on the new Stata 12 command, mi impute chained, to perform multivariate imputation using chained equations (ICE), also known as sequential regression imputation. ICE is a flexible imputation technique for imputing various types of data. The variable-by-variable specification of ICE allows the user to impute variables of different types by choosing the appropriate method for each variable from several univariate imputation methods. Variables can have an arbitrary missingdata pattern. By specifying a separate model for each variable, users are able to incorporate a number of important characteristics, such as ranges and restrictions within a subset, specific to each variable. Other new features in multiple imputation in Stata 12 will also be discussed.