|
![](http://www.statmodel.com/discussion/icons/csc/1px.gif) |
Growth factor covariances with quadra... |
![Previous](http://www.statmodel.com/discussion/icons/csc/navgen_arrow_left.gif) ![](http://www.statmodel.com/discussion/icons/csc/1px.gif)
|
Message/Author |
|
Gareth posted on Thursday, July 15, 2010 - 1:40 am
|
|
|
Example 6.16 (two-part growth model) in the user's guide recommends fixing growth factor covariances to zero. What would you recommend if adding a quadratic factor? For example: iu su qu | bin1@0 bin2@.1 bin3@.2 bin4@.3; iy sy qy | cont1@0 cont2@.1 cont3@.2 cont4@.3; su-qu@0; iu WITH sy-qy@0; |
|
|
This is not a recommendation. It is a way to reduce the number of dimensions of integration from three to one. |
|
Back to top |
|
|