Very well written piece by @zeynep about the difference between fundamental models (weather forecasting) and statistical models (most election models) https://www.nytimes.com/2020/11/01/opinion/election-forecasts-modeling-flaws.html?action=click&module=Opinion&pgtype=Homepage …
-
-
But isn't most of the current modeling fervor (deep learning) around statistical models and haven't they shown impressive results (in spite of their limitations)?
-
The important parameter here is how much training data you have for your model. If N is small (like N=12 in the case of election results) then a statistical model with a large number of parameters will not be a very good solution.
- Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.