Path Analysis with different groups a... PreviousNext
Mplus Discussion > Structural Equation Modeling >
Message/Author
 Orig posted on Sunday, September 02, 2012 - 9:07 pm
Hi,

i want to run a path analysis and i got one dataset, for three groups:
treatment_1, treatment_2, control

the three groups only differ in an exogenous shock

_________________________________________

the data contain the groups in form of two dummy variables as follows:

treat12 = 0 (treatment 1)
treat12 = 1 (treatment 2)

t1co = 0 (treatment 1)
t1co = 1 (control-group)

_________________________________________

Treatment 2 is in the focus of the analysis. What i already got is a fitted model for the "Treatment 2-Analysis".

My problem is:
I want to know, if the effect of treatment 2 generated in a variable, differs from treatment 1, but i donīt know how to do this, when i just got these two dummies.

example:

treat2 --> x ---> y

to account for treat1 :

treat1 --> y

but i dont know how to "build" the variable: treat1
 Linda K. Muthen posted on Monday, September 03, 2012 - 7:27 am
It looks like you do your dummy variables incorrectly. Try:

DEFINE:
tx1 = 0;
IF (treat1 EQ 1) THEN tx1=1;
tx2 = 0;
IF (treat2 EQ 1) THEN tx2=1;

MODEL:
y ON tx1 tx2;

The difference in the slopes is the difference in the treatment effects.
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: