|
![](http://www.statmodel.com/discussion/icons/csc/1px.gif) |
Specifying a Saturated Model |
![Previous](http://www.statmodel.com/discussion/icons/csc/navgen_arrow_left.gif) ![](http://www.statmodel.com/discussion/icons/csc/1px.gif)
|
Message/Author |
|
Anonymous posted on Friday, October 03, 2003 - 3:10 am
|
|
|
Hi All: I would like to know if the syntax below can be written more compactly. Specifically, is there a more efficient way to say that variables not in the regression model should correlate freely with each other and with the variables in the regression model? TITLE: Regression Model with FIML Estimation DATA: FILE IS "c:\ndri\gmi\data\ajda.dat" ; VARIABLE: NAMES ARE ID ALB ALE DRB DRE DYB DYE ATTND GMI ; USEVARIABLES ARE ALB ALE DRB DRE DYB DYE ATTND GMI ; MISSING ARE ALL (-9999) ; ANALYSIS: TYPE IS MISSING H1 MEANSTRUCTURE ; ESTIMATOR IS ML ; MODEL: DYE ON DYB GMI ; DYE DYB GMI WITH ATTND ALB ALE DRB ; ATTND WITH ALB ALE DRB DRE ; ALB WITH ALE DRB DRE ; ALE WITH DRB DRE ; DRB WITH DRE ; OUTPUT: STAND ; Thanks for any input. |
|
|
I don't see any shortcut other than using the list function. |
|
Back to top |
|
|