Testing causality with multi-level data PreviousNext
Mplus Discussion > Multilevel Data/Complex Sample >
Message/Author
 David Schiefer posted on Friday, March 09, 2012 - 3:24 am
Hello,

I want to test the causal direction of a relationship between a group-level variable (nation-level scores) and an individual-level variable. In particular, in a multi-country sample I want to test whether culturally-shared values (level-2 variable) impact attitudes of individuals, or whether, instead, individual attitudes impact culture-level values. Is there a technique to do that with MPlus?


Best regards
David
 Linda K. Muthen posted on Friday, March 09, 2012 - 3:41 pm
The only way to have an group-level variable influence and individual-level variable is it it influences the group part of the individual-level variables, for example,

%WITHIN%
y;
%BETWEEN%
y ON w;

where y is an individual-level variable and w is a group-level variable.
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: