Computational protocol: Rescuing Suboptimal Patient-Reported Outcome Instrument Data in Clinical Trials: A New Strategy

Similar protocols

Protocol publication

[…] Data from the two trials were analyzed separately and in parallel. The normality of each variable was checked in order to choose appropriate analysis approaches. Chi-square tests were applied to categorical data, and analysis of variance (ANOVA) or Kruskal-Wallis tests were applied to continuous data. Demographic and disease characteristics of the participants at baseline were summarized and compared across the three arms within each of the two trials. Preliminary comparisons of change from baseline on cognitive abilities as measured by the original and refined RBANS, within each of the two trials, were implemented. In comparing the original RBANS with the refined RBANS, we focused on providing consistent changes in cognitive scores. Comparing p-values would be flawed given the lack of power in these historical data (inadequate sample size) for assessing these secondary outcome measures [,]. Post hoc power analysis and sample size estimation were implemented to address the lack of power and small sample size issues. SPSS (Version 23, IBM Corp., Armonk, NY, USA) and SAS (Version 9.4, SAS Institute Inc., Cary, NC, USA) were used for data preparation and analysis. G*Power (Version, University of Düsseldorf, Düsseldorf, Germany) [,]) was used for post hoc power analysis and sample size estimation. […]

Pipeline specifications

Software tools SPSS, G*Power
Application Miscellaneous
Organisms Homo sapiens