Within-person repeated measures corre... PreviousNext
Mplus Discussion > Dynamic Structural Equation Modeling >
Message/Author
 joz posted on Friday, July 24, 2020 - 8:02 am
I am using DSEM without random slopes (T is small; N large).

I am doing within-person correlations between the following (assessed daily)
P and X; P and Y; N and X; N and Y

X and Y are highly correlated.

1) Is the following syntax correct?
2) Should I use TYPE = TWOLEVEL or TWOLEVEL RANDOM?
3) how do I control for Y in within-person correlations of P and X in the %within model (e.g. P with X)?


CLUSTER = id;
USEVAR = P N X Y;
Missing = ALL(-999);

ANALYSIS:
TYPE = TWOLEVEL;
MODEL:

%WITHIN%
P with X;
P with Y;
N with X;
N with Y;
P with N;

%BETWEEN%
P N X Y;
P with X;
P with Y;
N with X;
N with Y;
P with N;

output: standardized cinterval;
 Tihomir Asparouhov posted on Friday, July 24, 2020 - 9:30 am
1) If you want to run a DSEM model you have to add something like that
lagvar=P(1);
MODEL:
%WITHIN%
P on P&1;

Also you are missing
X with Y;
in your model

2) It doesn't matter

3) You can use interaction modeling
https://www.statmodel.com/download/LVinteractions.pdf
http://statmodel.com/download/WebNote23.zip
but honestly I am not sure you need to go there. Try first
P on X Y;
Back to top
Add Your Message Here
Post:
Username: Posting Information:
This is a public posting area. Enter your username and password if you have an account. Otherwise, enter your full name as your username and leave the password blank. Your e-mail address is optional.
Password:
E-mail:
Options: Enable HTML code in message
Automatically activate URLs in message
Action: