Alright folks I could use some help on a project. I want to predict the number of kills for league of legends players in a match using a multinomial; effectively trying to divvy up the total team kills to each player. To start I wanted to make a model with a player effect that is hierarchical. The c…

You can get back to the multinomial setup by sorting the long data by match_id (so that every 5 rows is a team) then doing a .reshape. That is, just add: new_df = new_df.sort_values(by='match_id') Then you can use match_idx created by pd.factorize as a sanity check: match_idx, matches = pd.factor…

Hierarchical Multinomial where groups change in each observation

Questions v5

ricardoV94 December 6, 2024, 7:29pm 2

This may be helpful for the shape issues: Distribution Dimensionality — PyMC 5.19.1 documentation

Topic		Replies	Views
Multinomial with Random Effects on panel data (shape issues) Questions	3	1409	March 13, 2018
Multinomial hierarchical regression with multiple observations per group ("Bad energy issue") Questions	22	3450	March 14, 2019
Prediction using sample_ppc in Hierarchical model Questions from_github	6	5004	December 14, 2017
Problem with multivariate hierarchical linear model Questions	3	725	May 31, 2018
Hierarchical Regression Model with Multiple Predictors Questions	1	814	June 21, 2018

Hierarchical Multinomial where groups change in each observation

Related topics