A new Bayesian paradigm for predition is proposed. Unlike the standard Bayes approach, which is tied to the underlying likelihood function, $\ell(y|\theta)$, this new aproach updates our prior belifs according to user-defined statistical criterion or loss function. Interestingly, we demonstrate how this new approach can generate posteriors over predictive densities, rather than posteriors over parameters.

Denver, Colorado (USA)
Click on the Slides button above to view the built-in slides feature.

Slides can be added in a few ways:

  • Create slides using Academic’s Slides feature and link using slides parameter in the front matter of the talk file
  • Upload an existing slide deck to static/ and link using url_slides parameter in the front matter of the talk file
  • Embed your slides (e.g. Google Slides) or presentation video on this page using shortcodes.

Further talk details can easily be added to this page using Markdown and $\rm \LaTeX$ math code.

David T. Frazier
DECRA Fellow and Associate Professor in Econometrics and Statistics

My research interests include simulation-based statistical theory and inference, approximate Bayesian analysis, forecasting and scoring rules.