Assessing the reasonableness of an imputation model
Maarten L. Buis
Multiple imputation is a popular way of dealing with missing values under the missing at random (MAR) assumption. Imputation models can become quite complicated, for instance, when the model of substantive interest contains many interactions or when the data originate from a nested design. This paper will discuss two methods to assess how plausible the results are. The first method consists of comparing the point estimates obtained by multiple imputation with point estimates obtained by another method for controlling for bias due to missing data. Second, the changes in standard error between the model that ignores the missing cases and the multiple imputation model are decomposed into three components: changes due to changes in sample size, changes due to uncertainty in the imputation model used in multiple imputation, and changes due to changes in the estimates that underlie the standard error. This decomposition helps in assessing the reasonableness of the change in standard error. These two methods will be illustrated with two new user written Stata commands.
In order to set up a list of libraries that you have access to,
you must first login
or sign up.
Then set up a personal list of libraries from your profile page by
clicking on your user name at the top right of any screen.