Collaborate on a PyMCon talk?

Short version: Would someone like to join a sort-of-adversarial collaboration with me on a PyMCon talk? I have built a simple version of a model using a grid algorithm. If someone wants to build a better model with PyMC, we could compare results.

Long version:

I am thinking of proposing a talk for PyMCon based on an example I used in Probably Overthinking It. The context is missing value imputation using item response theory. My implementation uses a grid algorithm, which is possible because I treat the “difficulty” parameters as fixed and estimate the “efficacy” parameters individually for each survey respondent.

I would be curious to see what difference it makes if we build a fully Bayesian version of the model that estimates difficulty and efficacy simultaneously. I think the results of the comparison would make a nice talk!

I can provide my implementation as a starting point and we can brainstorm options for the better model, but I’d need someone comfortable with implementing the better model in PyMC.


That’s a great idea! I might suggest pitching this idea at next week’s “Let’s Work on Your PyMCon Talk Idea” event. Not only would you get feedback on the idea, but you might find some “adversaries” as well.

I really like the idea. If nobody steps in I’ll be happy to collaborate, otherwise I’m happy to let others take the spotlight.

I’m a big fan of the Think Bayes book btw!

If you go ahead with this idea I propose that the “discussion meeting” is recorded. In blog posts, books, etc we always see the final version. Showing what a working session for how to expert model builders talk and challenge each other is harder to find.