RDSEM longitudinal mediation PreviousNext
Mplus Discussion > Dynamic Structural Equation Modeling >
Message/Author
 Andrew Johnson posted on Tuesday, July 14, 2020 - 12:34 am
If I want to test whether there is a non-zero indirect pathway in the cross-lagged relationships from x --> m --> y, would the following syntax be correct?

MODEL:
%WITHIN%
x m y ON TIME;

m_to_m | m^ ON m^1;
x_to_x | x^ ON x^1;
y_to_y | y^ ON y^1;

x_to_m | m^ ON x^1;
y_to_m | m^ ON y^1;

m_to_x | x^ ON m^1;
y_to_x | x^ ON y^1;

x_to_y | y^ ON x^1;
m_to_y | y^ ON m^1;


%BETWEEN%
m x y;
m_to_m-m_to_y;
[x_to_m m_to_y] (A B);

MODEL CONSTRAINT:
NEW(IND);
IND = A * B;

Thanks!
 Bengt O. Muthen posted on Tuesday, July 14, 2020 - 5:46 pm
The syntax looks ok. But the topic of mediation with longitudinal data is complex. See for instance the Maxwell-Cole articles - 2007 in Psych Methods and 2011 in MBR.
 Andrew Johnson posted on Tuesday, July 14, 2020 - 6:51 pm
Excellent. Thanks Bengt, I'll have a look at those papers now
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: