|
|
Parallel process model with interations |
|
Message/Author |
|
|
Hi there, I am running a parallel process model, with the intercept of the second process centered on the final time point. I would like to test whether the interaction between an exogenous variable (x) and the slope of the first process (s1) predicts the intercept and slope of the second process. I created an interaction term between s1 and x using the XWITH command. The model runs well, but does not provide fit statistics typical with latent growth models (i.e., without including the interaction). Is it no longer a LGM (given the TYPE = RANDOM)? Are these analyses appropriate? Below is my syntax. Many thanks. VARIABLE: NAMES ARE p1 p2 p3 p4 p5 d1 d2 d3 d4 d5 X; USEVARIABLES ARE p1 p2 p3 p4 p5 d1 d2 d3 d4 d5 X; MISSING ARE p1 p2 p3 p4 p5 d1 d2 d3 d4 d5 X (9999); ANALYSIS: TYPE = RANDOM MODEL: i1 s1 | p1@0 p2@1 p3@2 p4@3 p5@4; i2 s2 | d1@-4 d2@-3 d3@-2 d4@-1 d5@0; Modxs1 | X XWITH s1; s2 ON i1 s1 x Modxs1; i2 ON i1 s1 x Modxs1; p1 with d1; p2 with d2; p3 with d3; p4 with d4; p5 with d5; OUTPUT: STAND TECH1 TECH3 TECH4; |
|
|
When means, variances, and covariances are not sufficient statistics for model estimation, chi-square and related fit statistics are not available. You can look at the fit before you add the interaction. See the FAQ Latent Variable Interactions on the website. |
|
Back to top |
|
|