Intercept/slope correlations PreviousNext
Mplus Discussion > Growth Modeling of Longitudinal Data >
Message/Author
 JM posted on Sunday, October 04, 2009 - 5:01 pm
I'm running a parallel proces LGM. How do I obtain/locate the correlation coefficient between the two intercepts and slopes in the output along with corresponding p-value?
 Amir Sariaslan posted on Sunday, October 04, 2009 - 5:17 pm
Following example 6.13 in the UG, you should have the following in your output:

s2 on i1
s1 on i2
i1 with i2
s1 with s2

If you don't have these, you might have misspecified your model.
 JM posted on Monday, October 12, 2009 - 1:49 pm
Amir,
Thanks, I have specified that, but which output value corresponds to the r value and associated p-statistic? I've seen reports citing the correlation coefficient and p-value, but I'm not sure where that is w/n the output. Thanks!
James.
 Amir Sariaslan posted on Monday, October 12, 2009 - 2:11 pm
James,
The output of example 6.13 will give you the following:


S1 ON
I2 0.329 0.025 13.197 0.000

S2 ON
I1 0.602 0.029 20.653 0.000

I2 WITH
I1 0.025 0.057 0.443 0.658

S2 WITH
S1 0.081 0.019 4.360 0.000

The values in the first column provides you with the regression coefficients (s2 on i1 and s1 on i2) and covariances (i2 with i1 and s2 with s1) while the last column provides the corresponding p-values. I hope that this is what you're looking for.

Sincerely,
Amir
Back to top
Add Your Message Here
Post:
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Password:
Options: Enable HTML code in message
Automatically activate URLs in message
Action: