I am doing the path analysis in Stata using gsem command. I have binary dependent variable, mediator is continuous variable and I have 5 independent variables that are nominal or ordinal scale.
Questions:
1. Is it better to do it in the Model building and estimation or to write a command (I dont get the same results)? My code is: gsem (DV<-MV, logit) (MV<- i.IV1 i.IV2 i.IV3 i.IV4 i.IV5, regress), nocapslatent
2. How can I standardise the coefficients across the hole model because I have logit and linear regression in the same time?
Thank you in advance
Questions:
1. Is it better to do it in the Model building and estimation or to write a command (I dont get the same results)? My code is: gsem (DV<-MV, logit) (MV<- i.IV1 i.IV2 i.IV3 i.IV4 i.IV5, regress), nocapslatent
2. How can I standardise the coefficients across the hole model because I have logit and linear regression in the same time?
Thank you in advance
