Q1: Delaney Mackenzie – You Don’t Know How Wrong You Are
Chat With Traders
00:00
How to Avoid Overfitting in Statistics
The gold standard for avoiding overfitting is something known as out of sample testing. You do all your model development and strategy development on one data set. But you've saved some of the data to test whether it's just fit to noise or if there are real patterns I found that will continue forward into the future. The problem is that you only have a finite number of tests, so generally you'll have to like save several out ofsample testing segments from your data.
Transcript
Play full episode
