Ontology highlight
ABSTRACT: Background
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.Methods
We designed a simulation study based on the Longitudinal Study of Australian Children, where the target analysis was the association between (i
SUBMITTER: De Silva AP
PROVIDER: S-EPMC6329074 | biostudies-literature | 2019 Jan
REPOSITORIES: biostudies-literature