This Shiny App is designed to help users define their priors in a linear regression with two regression coefficients. Using the same example as in the software tutorials on this website, users are asked to specify their plausible parameter space and their expected prior means and uncertainty around these means. The PhD-delay example has been used an easy-to-go introduction to Bayesian inference. In this example the linear and quadratic effect of age on PhD-delay are estimated. Users learn about the interaction between a linear and a quadratic effect in the same model, about how to think about plausible parameter spaces, and about specification of normally distributed priors for regression coefficients. More information about the data and the model can be found here.
We are continuously improving the tutorials so let me know if you discover mistakes, or if you have additional resources I can refer to. The source code is available via Github. If you want to be the first to be informed about updates, follow me on Twitter.
Click on the preview to open your interface!
The app is self-explanatory. Users can just follow the 4 steps listed in the left side bar and answer the various questions asked.
This project is funded by the Netherlands organization for scientific research (NWO);grant number VIDI-452-14-006. Purpose of the service 'utrecht-university.shinyapps.io' is to provide a digital place for trying out, evaluating and/or comparing methods developed by researchers of Utrecht University for the scientific community worldwide. The app and its contents may not be preserved in such a way that it can be cited or can be referenced to. The web application is provided 'as is' and 'as available' and is without any warranty. Your use of this web application is solely at your own risk. By using this app you agree to be bound by the above terms.