CAMIS - A PHUSE DVOST Working Group

Introduction to CAMIS

Comparing Analysis Method Implementations in Software (CAMIS) is a cross-industry PHUSE DVOST Working Group, run in collaboration with members from PHUSE, PSI, ASA and IASCT. In addition to issue comments, which are hosted in the GitHub Repository, we meet monthly on the 2nd Monday of each month. If you would like to join us please contact us at workinggroups@phuse.global.

Motivation

The goal of this project is to demystify conflicting results in statistical analysis methods and results between primarily SAS, R, and Python programming languages by providing comparisons and comprehensive explanations of similarities and differences. Many discrepancies have been discovered in statistical analysis results between these and other programming languages. The differences in results are due to fundamental approaches implemented by each language, which are each correct in their own right. The fact that these differences exist is a challenge, especially related to sponsor companies when submitting to a regulatory agency.

In its Statistical Software Clarifying Statement, the US Food and Drug Administration (FDA) states that it “FDA does not require use of any specific software for statistical analyses” and that “the computer software used for data management and statistical analysis should be reliable.” Observing differences across languages can reduce the analyst’s confidence in reliability and, by understanding the source of any discrepancies, one can reinstate confidence in reliability. CAMIS seeks to explore and explain some of the differences and similarities in statical analysis methods between these languages to ease these concerns.

Repository

The repository below provides examples of statistical methodology in different software and languages, along with a comparison of the results obtained and description of any discrepancies.

Methods R SAS Python Comparison
Summary Statistics Rounding R SAS Python R vs SAS
R SAS Python R vs SAS
R SAS Python R vs SAS
General Linear Models One Sample t-test R SAS Python R vs SAS
R SAS Python R vs SAS
R SAS Python R vs SAS
R SAS Python R vs SAS
R SAS Python R vs SAS
R SAS Python R vs SAS
R SAS Python R vs SAS
Generalized Linear Models Logistic Regression R SAS Python R vs SAS
R SAS R vs SAS
Non-parametric Analysis Wilcoxon signed rank R SAS/ StatXact R vs SAS
R SAS R vs SAS
R SAS Python R vs SAS
R SAS R vs SAS
R SAS R vs SAS
R SAS
Categorical Data Analysis Binomial test R SAS Python
R SAS R vs SAS
R
R SAS Python R vs SAS
R SAS R vs SAS
R SAS R vs SAS
Repeated Measures Linear Mixed Model (MMRM) R SAS R vs SAS
Multiple Imputation - Continuous Data MAR MCMC
R SAS
R
Multiple Imputation - Continuous Data MNAR Tipping Point (Delta Adjustment) R SAS R vs SAS
R SAS R vs SAS
Correlation Pearson's/ Spearman's/ Kendall's Rank R SAS Python R vs SAS
Survival Models Kaplan-Meier Log-rank test and Cox-PH R SAS R vs SAS
R SAS R vs SAS
R
R
R SAS R vs SAS
R SAS R vs SAS
SAS
Sample size/ Power calculations Intro to Sample Size Summary
R SAS
R SAS
R SAS
R
R SAS/ StatXact
R East East vs R
Causal inference/ Machine learning Intro to Machine Learning Summary
R vs SAS
R
R
R
NA NA
Other Methods Survey statistics R SAS Python R vs SAS vs Python