What question did this study set out to answer?

To evaluate how cluster randomized trials address missing data and account for clustering in their primary outcome analyses.

February 9, 2016TrialsOpen Access

Statistical analysis and handling of missing data in cluster randomized trials: a systematic review

View Full Paper

Ask AI

Bookmark

Authors

MFMallorie H. FieroUnited States Food and Drug Administration SHShuang HuangAmgen (United States)EOEyal OrenUniversity of Port Harcourt

Discussion

Member takes

Implication

Systematic review reveals widespread missing data and suboptimal handling in cluster randomized trials, highlighting the need for robust methods and sensitivity analyses to minimize bias.

Key Points

To evaluate how cluster randomized trials address missing data and account for clustering in their primary outcome analyses.
Conducted a systematic review of cluster randomized trials published between August 2013 and July 2014 across PubMed, Web of Science, and PsycINFO (N = 86 trials).
Two independent reviewers extracted trial characteristics, the extent of missing outcome data, handling methods in primary and sensitivity analyses, and whether analyses operated at the cluster or individual level.
Missing outcome data occurred in 80 of 86 trials (93%), with a median of 19% missing individual data per trial (range 0.5% to 90%).
Complete case analysis was the primary strategy in 44 trials (55%), followed by mixed models in 18 (22%), single imputation in six (8%), unweighted generalized estimating equations in four (5%), and multiple imputation in two (2%).
Clustering was accounted for in the primary analysis of 67 trials (78%), while only 14 trials (16%) reported sensitivity analyses for missing data.

Cite This Study

Fiero et al. (2016) studied this question.

synapsesocial.com/papers/6a00aef7b124fe581985fefd https://doi.org/10.1186/s13063-016-1201-z

View Full Paper

Ask AI

Bookmark

Implication

Systematic review reveals widespread missing data and suboptimal handling in cluster randomized trials, highlighting the need for robust methods and sensitivity analyses to minimize bias.

Statistical analysis and handling of missing data in cluster randomized trials: a systematic review

Discussion

Member takes

Implication

Key Points

Cite This Study

Statistical analysis and handling of missing data in cluster randomized trials: a systematic review

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider