MeRGE Expo 2: Stan with bbr - About the MeRGE Expo

The Expo demonstrates using bbr.bayes in a typical Bayesian exposure-response modeling and simulation (M&S) workflow, including model fitting, model evaluation, and model summarization. This demonstration uses the same processes and suite of tools used at Metrum Research Group (MetrumRG) to ensure traceable and reproducible pharmacometrics research; however, it is not meant to be a complete vignette on using all of the features of bbr.bayes or the other tools used in the workflow. Links are provided in the tools section of the expo that shares additional information about each of the tools used.

What you’ll find in this Expo:

A description of the data and statistical models fitted to the data.
Our approach to M&S activities and reporting.
Access to example code in a GitHub repository.
Information and vignettes on MetrumRG’s suite of tools.

The diagram below illustrates the end-to-end process of a typical project from setup through completion. (Click through to visit the PDF with hyperlinks.)

This analysis was performed on Metworx, our platform as a service (PaaS) for high-performance elastic cloud computing; however, Metworx is not required to use the tools and process illustrated here.

This Expo demonstrates how to get started with the suite of tools that we use at Metrum Research Group to ensure traceable and reproducible pharmacometrics research. We proceed step-by-step through fitting a simple non-linear mixed effects model using Stan. We chose this example to illustrate a functional workflow of these tools with an understanding that some standards (e.g., sample sizes, etc) are simplified relative to the complexities of many typical analyses.

For comments, questions, or more information about any of the tools or work process demonstrated here, please contact us.