Abstract

Recent years have seen an explosion of use cases for generative AI. People are using AI to do research, write papers, summarize articles, and write code. At first, the quality of the output was not very good. Yet with each new release, the output is getting better and better. It is now feasible to perform tasks that previously would not be considered. In this presentation, we will explore the topic of code translation between SAS® and R using ChatGPT®. The presentation will first provide an overview of how to perform such a translation. We will then elaborate on a list of tips and tricks to make the machine translation better. Finally, we will point out some limitations of the technology and tell you what to watch out for. The presentation will hopefully present you with enough information to try translating some code yourself.

David J. Bosak is the Chief Software Architect at Archytas Clinical Solutions. He has been a consultant to pharma and non-pharma companies for over 28 years. He has extensive experience creating solutions in SAS, .NET, database, and web technologies. Currently obsessed with R, he has become an active package developer, and has 12 R packages published on CRAN.

Brian Varney has been a statistical programmer and statistician with Experis for over 35 years. He has spent time programming and training in SAS and R, architecting and deploying analytics environments, and providing data analysis to pharmaceutical and financial industries. In his spare time, Brian enjoys camping, traveling, rugby, and soccer.