|
Message/Author |
|
Joy Choi posted on Thursday, April 11, 2013 - 5:35 pm
|
|
|
I am running attrition analysis using sex, income, maternal depression with IV (attachment) and DV (social emotioanl functioning outcomes using growth curve midpoint intercept). This is one of my syntax for this analysis, but results is weird and not presenting anything. MODEL: ! INTERCEPT LOADINGS I_bex BY bexk@1 bex1@1 bex2@1 bex3@1 bex4@1 bex5@1 bex6@1; S_bex BY bexk@-3 bex1@-2 bex2@-1 bex3@0 bex4@1 bex5@2 bex6@3; ! REGRESSION I_bex sex incom mdep on attchment; I_bex sex incom mdep on other; * bex: externalizing behavior problems mdep: maternal depression at the child's age of 1 month other: sort of missing data. Among entire sample without attachment data. Questions are: 1. what is wrong with this syntax? 2. How do I compare "attachment" and "other"? chi-square differences or model fit? |
|
|
1. The syntax is not a properly specified growth model. I would suggest using the | language which sets the model up for you and also has defaults appropriate for growth models: i_bex S_bex | bexk@-3 bex1@-2 bex2@-1 bex3@0 bex4@1 bex5@2 bex6@3; 2. If attachment and other are both binary, you can compare the coefficients using MODEL TEST. |
|
Back to top |
|
|