Is there a pkg for calculating cross-validated (k fold) fit measures for #SEM in #rstats? Seems possible with Mplus http://www.statmodel.com/discussion/messages/9/12127.html?1389902731 …
-
there's ecva in lavaan as a fit statistic - but as I think it's asymptoticallt equivalent to aic might not be worth hassle
I've learned not to trust analytic solutions to fit when one can just as easily use k fold cross validation. :)
-
-
well running k folds manually in a loop is pretty simple right?
-
I run sem powe analyses by hand, easier to specify models than canned power solutions and more flexible..
-
In theory 1) fit on training data save all parameters 2) fit using test data and constrain all the parameters to those found in (1)
-
hmm good point that wouldn't be fun
-
Could be done with a fancy function, but that's one huge model string to auto-generate!
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.