Imputation of repeatedly observed multinomial variables in longitudinal surveys

ABSTRACT

It is now a standard practice to replace missing data in longitudinal surveys with imputed values, but there is still much uncertainty about the best approach to adopt. Using data from a real survey, we compared different strategies combining multiple imputation and the chained equations method, the two main objectives being (1) to explore the impact of the explanatory variables in the chained regression equations and (2) to study the effect of imputation on causality between successive waves of the survey. Results were very stable from one simulation to another, and no systematic bias did appear. The critical points of the method lied in the proper choice of covariates and in the respect of the temporal relation between variables.

KEYWORDS:

• Causality
• Chained equations
• Longitudinal survey
• Missing data
• Multiple imputation

MATHEMATICS SUBJECT CLASSIFICATION:

• Primary 62
• Secondary 62D05
• 62P25

Funding

This research was supported by the Swiss Tobacco Prevention Fund and by the Swiss National Centre of Competence in Research LIVES, which is financed by the Swiss National Science Foundation.