Can we improve the statistical analysis of stroke trials? Statistical re-analysis of functional outcomes in stroke trials

Bath, Philip M.W.; Optimising Analysis of Stroke Trials Collaboration, OAST

Abstract

Background and Purpose—Most large acute stroke trials have been neutral. Functional outcome is usually analyzed usinga yes or no answer, eg, death or dependency versus independence. We assessed which statistical approaches are mostefficient in analyzing outcomes from stroke trials.Methods—Individual patient data from acute, rehabilitation and stroke unit trials studying the effects of interventionswhich alter functional outcome were assessed. Outcomes included modified Rankin Scale, Barthel Index, and “3questions”. Data were analyzed using a variety of approaches which compare 2 treatment groups. The results for eachstatistical test for each trial were then compared.Results—Data from 55 datasets were obtained (47 trials, 54 173 patients). The test results differed substantially so thatapproaches which use the ordered nature of functional outcome data (ordinal logistic regression,ttest, robust ranks test,bootstrapping the difference in mean rank) were more efficient statistically than those which collapse the data into 2groups (
2; ANOVA,P
0.001). The findings were consistent across different types and sizes of trial and for thedifferent measures of functional outcome.Conclusions—When analyzing functional outcome from stroke trials, statistical tests which use the original ordered dataare more efficient and more likely to yield reliable results. Suitable approaches included ordinal logistic regression,ttest, and robust ranks test.

Citation

Bath, P. M., & Optimising Analysis of Stroke Trials Collaboration, O. (2007). Can we improve the statistical analysis of stroke trials? Statistical re-analysis of functional outcomes in stroke trials. Stroke, 38(6), https://doi.org/10.1161/STROKEAHA.106.474080

• Journal Article Type: Article
• Acceptance Date: Nov 21, 2006
• Online Publication Date: Apr 26, 2007
• Publication Date: Jun 1, 2007
• Deposit Date: Aug 22, 2008
• Publicly Available Date: Aug 22, 2008
• Journal: Stroke
• Print ISSN: 0039-2499
• Electronic ISSN: 1524-4628
• Publisher: American Heart Association
• Peer Reviewed: Peer Reviewed
• Volume: 38
• Issue: 6
• DOI: https://doi.org/10.1161/STROKEAHA.106.474080
• Keywords: stroke; randomised controlled trial; statistical analysis
• Public URL: https://nottingham-repository.worktribe.com/output/1016779
• Publisher URL: http://stroke.ahajournals.org/content/38/6/1911
• Contract Date: Aug 22, 2008