

Seemingly unrelated regression 

Message/Author 


I'd like to run a seemingly unrelated regression in Mplus, but haven't seen anything on the site about SUR. I did, however, find the code shown below at http://www.ats.ucla.edu/stat/mplus/output/sureg.htm . Could anyone confirm whether this would be the appropriate way to run SUR in Mplus? Many thanks! Title: Seemingly unrelated regression; Data: File = hsb2.dat ; Variable: Names = id female race ses schtyp prog read write math science socst; usevar = read socst write math science; Analysis: Type = meanstructure ; model: read on write math science; socst on write math science; 


According the the ATS website, this is correct. I have no reason to doubt this. 


Thank you. 


As a followup, would there be any methodological problems with including a CFA in the same model? For example looking back at the example in my original post, could one include indicators of some of the constructs, something like this? Title: Seemingly unrelated regression; Data: File = hsb2.dat ; Variable: Names = id female race ses schtyp prog read1 read2 read3 write math1 math2 math3 science socst; usevar = read1 read2 read3 socst write math1 math2 math3 science; Analysis: Type = meanstructure ; model: math by math1 math2 math3; read by read1 read2 read3; read on write math science; socst on write math science; Thanks, Robert 


I can't see that this would be a problem. 


Thank you again. 

Back to top 

