1
$\begingroup$

I have a question regarding Leave One Out Cross Validation (LOOCV):

When I use the method, I will have several regression outputs, one for each individual in my sample. How is this usually reported? Can I report means of the coefficient-estimates and standard-errors? That does not seem quite right to me.

Or are the results of the LOOCV-Method not reported in the usual manner, with coefficient estimated and standard errors?

$\endgroup$

1 Answer 1

1
$\begingroup$

The results of LOOCV are supposed to be aggregated and averaged in some meaningful way, depending on whether it's a classification or regression problem. That is how good your model is at predicting new values. You mentioned coefficients and standard errors... CV is done for predictive purposes, not for interpretation or coefficient estimation.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.