Statistical Power and Performance of Strategies to Analyze Composites of Survival and Duration of Ventilation in Clinical Trials
All methods have good control of type 1 error rates (i.e., avoid false positive findings). When data are simulated using a proportional odds model, the t test and ordinal models have the highest relative power (92% and 90%, respectively), followed by competing risk models. When the data are simulated using survival models, the competing risk models have the highest power (100% and 92%), followed by the t test and a ten-category ordinal model. All models struggled to detect the effect of the intervention when the treatment only affected one of mortality and duration of ventilation. Overall, the best performing analytical strategy depends on the respective effects of treatment on survival and duration of ventilation and the underlying distribution of the outcomes. The evaluated models each provide a different interpretation for the treatment effect, which must be considered alongside the statistical power when selecting analysis models.
Authors
- Martin Urner (ORCID: https://orcid.org/0000-0003-1133-4885)
- Christopher J. Yarnell (ORCID: https://orcid.org/0000-0001-5657-9398)
- Ewan C. Goligher (ORCID: https://orcid.org/0000-0002-0990-6701)
- Daniel Francis McAuley (ORCID: https://orcid.org/0000-0002-3283-1947)
- Anna Heath (ORCID: https://orcid.org/0000-0002-7263-4251)
- Anders Granholm (ORCID: https://orcid.org/0000-0001-5799-7655)
- Eddy Fan (ORCID: https://orcid.org/0000-0002-1210-9914)
- Ziming Chen (ORCID: https://orcid.org/0000-0002-9783-0865)
- Michael O. Harhay
Institutions
- Queen's University Belfast (GB)
- University Health Network (CA)
- University of Ulster (GB)
- University of Toronto (CA)
- Scarborough Health Network (CA)
- Hospital for Sick Children (CA)
- Toronto General Hospital (CA)
- Copenhagen University Hospital (DK)
- Rigshospitalet (DK)
- Public Health Ontario (CA)
- Royal Victoria Hospital (GB)
- SickKids Foundation (CA)
- Institute for Clinical Evaluative Sciences (CA)
- Toronto General Hospital Research Institute
- University College London (GB)
- University of Pennsylvania (US)
Publication Details
- Journal
- Critical Care Explorations
- Published
- 2024-09-20
- DOI
- https://doi.org/10.1097/cce.0000000000001152
- Citations
- 1
- Primary Topic
- Frailty in Older Adults
- Type
- article
- Field-Weighted Citation Impact
- 0.34
Funders
- University College London
- University of Toronto
- National Institutes of Health
- Natural Sciences and Engineering Research Council of Canada
- National Heart, Lung, and Blood Institute