glmcmp: Generalized Linear Models with Conditional Means Priors in R

• Activity Number: 392 - What Do the Experts Believe? Leveraging Expert Knowledge to Develop Robust Informative Prior Belief Distributions to Aid Decision Making in Drug and Medical Device Development
• Type: Topic Contributed
• Date/Time: Tuesday, August 1, 2017 : 2:00 PM to 3:50 AM
• Sponsor: Section on Bayesian Statistical Science
• Author(s): David Kahle* and James Stamey and Michael Sonksen and Michael W. Seaman, Jr. and Karen Price and Fanni Natanegara
• Companies: Baylor University and Baylor University and Eli Lilly and Company and Baylor University and Eli Lilly and Eli Lilly and Company

Abstract

One of the key advantages of the Bayesian paradigm is the ability to inject expert opinion directly into the modeling process. In this talk we introduce glmcmp, an R package that provides novel data structures and methods to facilitate the use of generalized linear models with conditional means priors in R and BUGS. Included in glmcmp is a highly extensible, pipeline based prior elicitation framework that conceptually organizes the elicitation process in a way that encourages a macroscopic view of the modeling process and is user-friendly.