Analysis of Longitudinal Outcome Data with Missing Values in Total Knee Arthroplasty.

TitleAnalysis of Longitudinal Outcome Data with Missing Values in Total Knee Arthroplasty.
Publication TypeJournal Article
Year of Publication2016
AuthorsKang, YGwi, Lee, JTaek, Kang, JYeal, Kim, GHye, Kim, TKyun
JournalJ Arthroplasty
Date Published2016 01 01
KeywordsAged, Algorithms, Analysis of Variance, Arthroplasty, Replacement, Knee, Data Collection, Data Interpretation, Statistical, Female, Humans, Longitudinal Studies, Male, Middle Aged, Models, Statistical, Osteoarthritis, Range of Motion, Articular, Research Design, Retrospective Studies, Sample Size, Surveys and Questionnaires

We sought to determine the influence of missing data on the statistical results, and to determine which statistical method is most appropriate for the analysis of longitudinal outcome data of TKA with missing values among repeated measures ANOVA, generalized estimating equation (GEE) and mixed effects model repeated measures (MMRM). Data sets with missing values were generated with different proportion of missing data, sample size and missing-data generation mechanism. Each data set was analyzed with three statistical methods. The influence of missing data was greater with higher proportion of missing data and smaller sample size. MMRM tended to show least changes in the statistics. When missing values were generated by 'missing not at random' mechanism, no statistical methods could fully avoid deviations in the results.

Alternate JournalJ Arthroplasty
PubMed ID26248852