Does anyone have any advice on how I can pool the R-Squared and Change in
R-Squared for linear regression with imputed data? The spss missing data
analysis program provides pooled unstandardized co-efficients and t ratios
but not pooled R-Squared or Change in R-Squared. Could I simply average
the R-squared or Change in R-squared accross the imputations for each
variable? When I asked the technical support people at IBM they said no,
but did not offer any explanation why.
Thank in advance for your help.
George
=====================
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
