Beyond SAS versus R: Making the Case for Open Source Software in Clinical Trials

• Activity Number: 100
• Type: Invited
• Date/Time: Monday, August 5, 2013 : 8:30 AM to 10:20 AM
• Sponsor: Section for Statistical Programmers and Analysts
• Author(s): Kevin Buhr*+
• Companies: University of Wisconsin
• Keywords: drug development ; data analysis ; advantages of open source ; supporting data monitoring committees

Abstract

In drug development, the case for using an open source system for a task is often made on the basis of a specific argument for the superiority of the particular system over the particular proprietary alternative for the particular task (e.g., R versus SAS for complex graphics) together with a general, defensive argument against perceived disadvantages of "open source in general". Where advantages of "open source in general" are mentioned, they are presented mostly abstractly. In this talk, I'll discuss some of the general attributes of open source projects (e.g., transparency, interoperability) that make them attractive for our industry and for reliable data and statistical analysis in particular, and I'll illustrate them with concrete examples taken from our group's work supporting data monitoring committees in interim monitoring of (mostly large, phase 3) drug trials.