Multiple imputation methods for handling missing values in a longitudinal categorical variable with restrictions on transitions over time: a simulation study
Open Access
- 10 January 2019
- journal article
- research article
- Published by Springer Nature in BMC Medical Research Methodology
- Vol. 19 (1) , 14
Abstract
Longitudinal categorical variables are sometimes restricted in terms of how individuals transition between categories over time. For example, with a time-dependent measure of smoking categorised as never-smoker, ex-smoker, and current-smoker, current-smokers or ex-smokers cannot transition to a never-smoker at a subsequent wave. These longitudinal variables often contain missing values, however, there is little guidance on whether these restrictions need to be accommodated when using multiple imputation methods. Multiply imputing such missing values, ignoring the restrictions, could lead to implausible transitions. We designed a simulation study based on the Longitudinal Study of Australian Children, where the target analysis was the association between (incomplete) maternal smoking and childhood obesity. We set varying proportions of data on maternal smoking to missing completely at random or missing at random. We compared the performance of fully conditional specification with multinomial and ordinal logistic imputation, and predictive mean matching, two-fold fully conditional specification, indicator based imputation under multivariate normal imputation with projected distance-based rounding, and continuous imputation under multivariate normal imputation with calibration, where each of these multiple imputation methods were applied, accounting for the restrictions using a semi-deterministic imputation procedure. Overall, we observed reduced bias when applying multiple imputation methods with restrictions, and fully conditional specification with predictive mean matching performed the best. Applying fully conditional specification and two-fold fully conditional specification for imputing nominal variables based on multinomial logistic regression had severe convergence issues. Both imputation methods under multivariate normal imputation produced biased estimates when restrictions were not accommodated, however, we observed substantial reductions in bias when restrictions were applied with continuous imputation under multivariate normal imputation with calibration. In a similar longitudinal setting we recommend the use of fully conditional specification with predictive mean matching, with restrictions applied during the imputation stage.Keywords
Funding Information
- National Health and Medical Research Council (1035261, 1104975, 1053609)
- State Government of Victoria (Victorian International Research Scholarship)
- University of Melbourne (Melbourne International Fee Remission Scholarship)
This publication has 46 references indexed in Scilit:
- The impact of missing data on analyses of a time-dependent exposure in a longitudinal cohort: a simulation studyEmerging Themes in Epidemiology, 2013
- A review of the reporting and handling of missing data in cohort studies with repeated assessment of exposure measuresBMC Medical Research Methodology, 2012
- Gaussian‐based routines to impute categorical variables in health surveysStatistics in Medicine, 2011
- Unpredictable bias when using the missing indicator method or complete case analysis for missing confounder values: an empirical exampleJournal of Clinical Epidemiology, 2010
- Comparison of techniques for handling missing covariate data within prognostic modelling studies: a simulation studyBMC Medical Research Methodology, 2010
- The design of simulation studies in medical statisticsStatistics in Medicine, 2006
- Does Maternal Smoking during Pregnancy Have a Direct Effect on Future Offspring Obesity? Evidence from a Prospective Birth Cohort StudyAmerican Journal of Epidemiology, 2006
- Statistical Issues in Life Course EpidemiologyAmerican Journal of Epidemiology, 2005
- Bias due to missing exposure data using complete‐case analysis in the proportional hazards regression modelStatistics in Medicine, 2003
- Multiple Imputation after 18+ YearsJournal of the American Statistical Association, 1996