Level-1 predictor level-2 outcome PreviousNext
Mplus Discussion > Multilevel Data/Complex Sample >
Message/Author
 Freya Glendinning posted on Tuesday, June 30, 2015 - 6:45 am
Hi,

I have three level-1 predictor variable's ('ZIMP ZSAT INTERACTION')
I have one level-2 outcome variable ('SE')

my data set is organised so that my predictor variables are not time points, but they are three separate data points for each individual. This means that the 'INDIVIDUAL' variable is organised like this (so essentially a grouping variable)-

1
1
1
2
2
2
3
3
3 etc.

I also have a 'NEED' variable where there are three needs for each individual, so in my data set NEED, next to individual looks like this:

1 1
1 2
1 3
2 1
2 2
2 3
3 1
3 2
3 3 etc.

I want to control for the differences between INDIVIDUAL and NEED and also look at the effects of ZSAT(x1) ZIMP(x2) AND INTERACTION(x3) ON SE(y)...

Is this Syntax I have created correct?

VARIABLE: NAMES ARE OBSERVATION INDIVIDUAL NEED SAT
ZIMP ZSAT INTERACTION SE RAI;
USEVARIABLES INDIVIDUAL NEED ZIMP ZSAT INTERACTION SE;
CLUSTER = INDIVIDUAL NEED;
WITHIN = ZIMP ZSAT INTERACTION;
DEFINE: CENTER ZIMP ZSAT INTERACTION (GROUPMEAN);
BETWEEN = SE;
ANALYSIS: TYPE = TWOLEVEL COMPLEX;
MODEL: %WITHIN%
SE ON ZIMP ZSAT INTERACTION;
SE@0
OUTPUT: SAMPSTAT;


Thank You!!!
 Bengt O. Muthen posted on Wednesday, July 01, 2015 - 5:21 pm
You should not have SE in a %Within% statement if it is a level-2 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: