male/female effects in Probit

[SarahHastley]

Hi,

I have a simple probit model, and I want to estimate the different marginal effects for male and female for the independent variable.

If I regress

probit depvar indepvar male*indepvar
mfx

Is the marginal effect on "male*indepvar" the marginal effect for males? and the marginal effect on "indepvar" the effect for females?

where male is coded 1 if they are male and 0 if they are female

Thanks.

[Stephen Jenkins]

(1) There should be a main effect for "male" in your regression specification:

probit depvar indepvar male  male*indepvar

(2) help mfx returns the following:

    mfx has been superseded by margins.  margins can do everything that mfx did and more.  margins syntax  differs from mfx; see margins.  mfx continues to work but does not support factor variables and will often fail if you do not run your estimation command under version control, with the version set to less than 11.  This help file remains to assist those who encounter an mfx command in old do-files and  programs.

To use margins properly, you also need to know about factor variables: help fvvarlist
[If you are not using the current version of Stata, you should be telling us in your post: see the forum FAQ.]

So, in sum, look at the help for margins and fvarlist, together with associated Manual entries.

[Richard Williams]

Also consider getting the new edition of Long & Freese's book:

http://www.stata.com/bookstore/regre...ent-variables/

The book does a good job of explaining various techniques for categorical data analysis. Their spost13 routines are like margins on steroids; they let you do a lot of interesting things pretty easily. You can also do

findit spost13_ado

to download and install their programs.

I am also a big fan of the mcp command. Do

findit mcp