Carina Wolf posted on Thursday, March 26, 2015 - 12:14 pm
I assume that on individual level intergroupcontact opportunity ("opport", single item) predicts intergroup friendship ("friend", three Items, is not modeled as latent factor). On the context level we have in addition percentage of immigrants ("percent") in district ("distric"). Here I assume that percentage of immigrants predicts intergroupcontact opportunity ("opport"). And percentage of immigrants predicts intergroup friendship - both directly and indirectly via the intergroup contact opportunity in neighbourhood. If I run the model, the following warning occurs: *** WARNING in MODEL command In the MODEL command, the following variable is a y-variable on the BETWEEN level and an x-variable on the WITHIN level. This variable will be treated as a y-variable on both levels: "opport" What should I do now? Thanks a lot in advance!
USEVARIABLES ARE opport percent friend; MISSING ARE ALL (777); CLUSTER IS distric; BETWEEN IS percent;
DEFINE: CENTER percent (GRANDMEAN); ANALYSIS: TYPE IS TWOLEVEL; MODEL: %WITHIN% friend ON opport; %BETWEEN% friend ON opport percent; opport ON percent; MODEL INDIRECT: friend IND percent;
With the code at the end of this message, tech 9 reports the following for every rep
"THE MODEL ESTIMATION TERMINATED NORMALLY
Errors for replication with data file DataX.csv:"
Here X is the rep number.
The only warning produced when analyzing data in a specific rep is
In the MODEL command, the following variable is a y-variable on the BETWEEN level and an x-variable on the WITHIN level. This variable will be treated as a y-variable on both levels: COV
I am assuming this warning is the cause of the errors to which tech 9 refers. Is this correct?
file is datalist.txt; type = montecarlo; Variable: names = School Treat Cov Dv; Usevariables = School Treat Cov Dv; Cluster = School; Between = Treat; Define: Center Cov (Grandmean); Analysis: Type = Twolevel; Model: %Within% Dv on Cov*.25; DV*.85; Cov*.85; %Between% Dv on Cov*.35 Treat*.5; DV*.15; Cov on Treat*0; [Cov*0]; Cov*.15;