Regression training and testing error

by dynamic89   Last Updated October 20, 2019 01:19 AM - source

Let’s say we fit a linear regression. What does the correlation between it’s training error and testing error say about the model, its performance or the data? What does a very low or very high correlation imply?

When I fit the same regression but with a ridge penalty, I found that the correlation between training and test error doesn’t change with the ridge penalty parameter lambda. Can I say something about the data?



Related Questions


Training RMSE higher than Validation RMSE in H2O

Updated November 25, 2018 11:19 AM


The Elements of Statistical Learning, Exercise 2.9

Updated October 30, 2017 00:19 AM