Multiple Imputation When Rate of Change Is The Outcome of Interest

Authors

Manisha Desai, Stanford UniversityFollow
Aya A. Mitani, Boston UniversityFollow
Susan W. Bryson, Stanford UniversityFollow
Thomas Robinson, Stanford UniversityFollow

Abstract

Little research has been devoted to multiple imputation (MI) of derived variables. We investigated various MI approaches for the outcome, rate of change, when the analysis model is a two-stage linear regression. Our simulations showed that competitive approaches depended on the missing data mechanism and presence of auxiliary terms.

DOI

10.22237/jmasm/1462075740