# Cross Validation

**URL:** <https://isgw-forum.colorado.edu/t/cross-validation/826>\
**Category:** Day 5\
**Created:** [June 8, 2026, 5:15pm UTC](https://isgw-forum.colorado.edu/t/cross-validation/826 "2026-06-08T17:15:54Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![anonymous](https://isgw-forum.colorado.edu/letter_avatar_proxy/v4/letter/a/8491ac/32.png) [@anonymous](https://isgw-forum.colorado.edu/u/anonymous)\
**Post date:** [June 8, 2026, 5:15pm UTC](https://isgw-forum.colorado.edu/t/cross-validation/826/1 "2026-06-08T17:15:54Z")

</div>

How many folds are ideal for cross validation?

> Replying to “How many folds are ideal for cross validation?”:

Often people use 5- or 10-fold depending on sample size. 10-fold CV will be more computationally expensive (e.g. when you run analysis on UKB-RAP)

> Replying to “How many folds are ideal for cross validation?”:

The general rule is you should have more folds with a smaller sample size. You could even do a leave-one-individual-out analysis to maximize the training sample size.