I am running simple linear regressions in both Mplus and SPSS to cross-validate my code and results. In general, the regressions are replicating in the two programs, except for just one of the models, and I think I've been able to isolate the variable that seems "problematic". Specifically, there is a signficant positive effect of A -> B in SPSS (p = 0.00) but the effect becomes negative and non-significant in Mplus. However, the dataset used in both programs is identical, and the reported means in both programs are identical too.
Any ides for troubleshooting? Or, is there any particular reason why there could be this discrepancy between just the one particular variable?
Here is my code: TITLE: read in raw data; DATA: file='c:\users\desktop\dyad.dat'; VARIABLE: names = var1 var2;