Dear all,
I am using GENERALIZED ESTIMATING EQUATIONS to ESTIMATE A MODEL.
I have correlated observations (ID), and 20 clustered data (cluster).
Example
id cluster Y sex X1 X2
1 1
2 1
3 1
20 2
21 2
22 2
23 2
…
100 10
102 10
102 10
….
Is very important that I take the CORRELATED OBSERVATION (ID) into account ?. I am not familiar with THIS PROCEDURE IN spss, but apparently thisIS OK
I have two procedure. ¿what is the better?
1.
GENLIN YI BY sex (ORDER=ASCENDING) WITH X1 X2
/MODEL sex X1 X2
INTERCEPT=YES
DISTRIBUTION=NORMAL
LINK=IDENTITY
/CRITERIA SCALE=MLE
PCONVERGE=1E-006(ABSOLUTE)
SINGULAR=1E-012
ANALYSISTYPE=3 CILEVEL=95
/EMMEANS TABLES=SEX SCALE=ORIGINAL
/REPEATED
SUBJECT=Cluster
WITHINSUBJECT=CHILDID
SORT=YES CORRTYPE=INDEPENDENT
ADJUSTCORR=YES COVB=ROBUST
/MISSING CLASSMISSING=EXCLUDE
/PRINT CPS DESCRIPTIVES MODELINFO FIT SUMMARY SOLUTION
/SAVE PEARSONRESID.
*2. Generalized Estimating Equations.
GENLIN Y BY SEX CLUSTER (ORDER=ASCENDING) WITH X1 X2
/MODEL SEX CLUSTER X1 X2
INTERCEPT=YES
DISTRIBUTION=NORMAL
LINK=IDENTITY
/CRITERIA SCALE=MLE
PCONVERGE=1E-006(ABSOLUTE)
SINGULAR=1E-012
ANALYSISTYPE=3 CILEVEL=95
/EMMEANS TABLES=SEX SCALE=ORIGINAL
/REPEATED
SUBJECT=Cluster
WITHINSUBJECT=CHILDID
SORT=YES CORRTYPE=INDEPENDENT
ADJUSTCORR=YES COVB=ROBUST
/MISSING CLASSMISSING=EXCLUDE
/PRINT CPS DESCRIPTIVES MODELINFO FIT SUMMARY SOLUTION
/SAVE PEARSONRESID.
Thanks by advance
Jesus
_________________________________________________________________
News, entertainment and everything you care about at Live.com. Get it now!
http://www.live.com/getstarted.aspx====================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
