Hacker News new | past | comments | ask | show | jobs | submit login
A Time Series Apologia (win-vector.com)
29 points by jmount on May 8, 2023 | hide | past | favorite | 3 comments



This is a nice and surprisingly important distinction that matters a lot in practice:

> Notice we get good out of sample performance. If we are judging on quality of out of sample predictions (and not on system identification or inference) then direct fitting k-step out predictors looks like a justifiable strategy.


Perhaps better to link just directly to the actual article rather than the borderline blogspam?





Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: