Hi all I would like to perform validation of a hierarchical model using LOO-CV. I would like to estimate the validation metric for both leaving out only one observation and leaving out an entire group of observations (LOGO-CV). Is this possible using arviz? If not, what is your suggested approach? …

Hi! You can choose between loo/logo with the log likelihood data you give to loo or waic functions. One quick example using the radon dataset (comes with ArviZ). We have 919 observations from a total of 85 counties, each county has a different number of observations. import arviz as az idata = az.…

LOO-CV for hierarcical model

Questions v5

Antonis April 4, 2023, 6:40pm 3

Thank you! This approach solves my problem.

Topic		Replies	Views
Leave on group out cross validation v5 modeling	8	1139	December 19, 2022
Can loo_i in arviz.loo be used to get an estimate of loo for the last 30 datapoints? v5 arviz	0	433	May 9, 2023
AUC with PSIS-LOO-CV Questions	2	781	May 23, 2020
Leave One Out Cross-validation and RMSE Questions from_github	11	3177	June 16, 2017
Calculating WAIC for models with multiple likelihood functions Questions	20	4626	October 26, 2020

LOO-CV for hierarcical model

Related topics