I would like to test the significance of difference between the coefficients in 2 probit models. I follow the code in Stata Manual:
. logit y1 x1
. estimates store M1
. logit y2 x2
. estimates store M2
. suest M1 M2
. test [M1]x1=[M2]x2
In my case, I re-phrased the above code:
. probit y1 x1 if group==0
. estimates store M1
. probit y1 x1 if group==1
. estimates store M2
. suest M1 M2
. test [M1]x1=[M2]x1
But I was only told by Stata that "equation M1 not found" so that I have to use "reg" model instead of "probit" to test the coefficient difference.
I am really thankful if anyone could kindly provide suggestions on the proper stata code. Thank you very much!
Related Posts with Testing coefficient difference in 2 probit models
How to use -graph combine- and typical twoway options with -meta forest-Dear all, I would like to present forest plots side by side, but -meta forest- does not work well w…
8 character dateHi, I need an 8 character date in order to use the "estudy" package (it's for the "evdate" option). …
Fixed effects omitted variables due to collinearity (xtreg, fe)Hello everyone, Hope you're well. First of all, I'm new to all of this. I'm struggling to identify …
Latent Class AnalysisHi Statalist I am performing Latent Class Analysis in STATA 14. I am using the following Code: gse…
System GMM - Interpreting the outputHello, I am estimating whether the total value of stocks traded and credit to the private sector ha…
Subscribe to:
Post Comments (Atom)
0 Response to Testing coefficient difference in 2 probit models
Post a Comment