overfitting & df's

[Tino Nsenene]

Dear All,

i would be grateful for any recommendations where I could find an
explanation of the phenomeon of "overfitting" - obviously, this measn there
are too many variables for too few data points - and how to diagnose it. Are
there are any particular statistical tests in Spss available ?

Thank you for your responses!
Tino

=====================
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

[Bruce Weaver]

Mike Babyak's article (which is more or less a book report on Frank Harrell's regression book) is very good.

http://www.psychosomaticmedicine.org/content/66/3/411.short
http://os1.amc.nl/mediawiki/images/Babyak_-_overfitting.pdf

HTH.

Tino Nsenene wrote

Dear All,

i would be grateful for any recommendations where I could find an
explanation of the phenomeon of "overfitting" - obviously, this measn there
are too many variables for too few data points - and how to diagnose it. Are
there are any particular statistical tests in Spss available ?

Thank you for your responses!
Tino

=====================
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