Timeline for Feature selection for "final" model when performing cross-validation in machine learning
Current License: CC BY-SA 2.5
3 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Aug 25, 2011 at 13:53 | comment | added | Dikran Marsupial | It is also questionable whether assymptotic results are of practical use when looking at datasets with a large number of features and comparatively few patterns. In that case the variance of the procedure is likely to be of greater practical importance than bias or consistency. The main value of LOOCV is that for many models it can be implemented at negligible computational expense, so while it has a higher variance than say bootstrapping, it may be the only feasible approach within the computaional budget available. That is why I use it, but I use something else for performance evaluation! | |
| Sep 3, 2010 at 0:17 | comment | added | user88 | Ok, to be clear -- I'm not saying LOOCV is a good idea for a big number of objects; obviously it is not, but Shao is not applicable here. Indeed in most of cases rules for LMs does not hold for ML. | |
| Sep 2, 2010 at 23:05 | history | answered | shabbychef | CC BY-SA 2.5 |