I have built a bayesian linear regression model using pymc3. On evalation, I found that the MAPE results (mean absolute percentage error) on training set is more the test set. what can be the reason for this as the same variable means are used for test set?

Bayesian linear regression

Mind-The-Data October 31, 2019, 1:11pm 4

Hmm. I would try another random splitting of train and test. And rerun the model.

Topic		Replies	Views
Predictions and evaluation of linear regression Questions	11	1866	November 22, 2018
Prediction by Bayesian linear regression Questions	7	1865	April 12, 2021
Comparing posterior predictive errors across samples Questions	0	404	October 7, 2020
Improve accuracy of probabilistic linear regression Questions	1	525	January 22, 2019
Do we need a testing set? Questions	9	5852	May 27, 2020