Hi, Listers,
I’m trying to make predictions using spatial temporal algorithm.
But I’m concerned with overfitting and not sure how I could address
problem. Cross validation won’t do as it’s going to create subsets of data with
data of some goe locations and some time point missings.
Any recommendations how we can tackle this?
Thanks!
=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
Locked
