top | item 44106590

(no title)

tlyleung | 9 months ago

Author here - funny to see this posted after a few years. Happy to answer any questions!

discuss

order

GreyZephyr|9 months ago

Did you ever try extending it out to other methods of probability estimation other than the forms of regression? I have only skimmed your excellent article, but I think you are first calculating the average probabilities from a regression model and then minimizing the loss to calculate Harville corrections for place and show markets? Is that correct or am I missing something here? I guess I am curious if there has been any improvement on using regressions for combining the various initial odds as I don't really follow the literature anymore.

tlyleung|9 months ago

Yes! There have been big improvements since then but they are beyond the scope of the post. I just wanted to reproduce the calculations in the paper using PyTorch.

Bill Benter subsequently replaced the multinomial logit model with a multinomial probit model, which assumes Normally distributed errors rather than errors that follow the Laplace distribution.

jeffreyrogers|9 months ago

How did you choose the artworks for the artworks section of your site?

tlyleung|9 months ago

It’s a hi-res artwork from Unsplash that I’ve sampled random croppings from.

fidotron|9 months ago

Great write up. [am idiot]

tlyleung|9 months ago

Sorry - to be clear this is just re-running the model detailed in Bill Benter’s 1995 paper (he uses the time period 1986-1993) on more recent time periods (1996-2003, 2006-2013, 2016-2023) using PyTorch.

4gotunameagain|9 months ago

Please read the first paragraph of the post again. The original author of the paper is Bill Benter, and the GP is the author of this excellent writeup.