A review of the handling of missing longitudinal outcome data in clinical trials

Table 1 Method of missing data handling

Primary approach to analysis	Papers
Complete case analysis	32
Mixed models	18
Simple imputation	14¹
LOCF/FOCB/Baseline Carried Forward	9
Average value either side Imputed	1
Simple algorithmic-based imputation	1
Mean of other patients values imputed	1
Median values imputed	1
Multiple imputation methods	4
Other non-imputation-based methods²	14
Exclusion based on amounts of missingness	6
Exclusion based on reasons for missingness	1
No missing data	9
Unclear	3

¹One paper which used a complete case analysis also used simple imputation as a secondary analysis. In Table2, this paper is included in the simple imputation section.
²Comparison of means, for example, t-test, RMANOVA.

ISSN: 1745-6215