Statalist The Stata Listserver

[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Re: Econometrically sound to use Mills ratio after mprobit?

From   "R.E. De Hoyos" <>
To   <>
Subject   st: Re: Econometrically sound to use Mills ratio after mprobit?
Date   Fri, 7 Apr 2006 17:45:36 +0100


I haven't come across such paper, however there have been several papers dealing with selectivity-adjustment using the conditional probabilities of a multinomial logit.

Check: -svyselmlog- (downloadable from SSC) and the references there.

The main point of debate is how to parameterize the conditional probabilities: (1) make a normal transformation, (2) include the cond. probabilities of the those categories not chosen, (3) semi-parametric methods.

If you come across such paper, please let me know. I would be interested in exploring the possibility of writing such a code.


----- Original Message ----- From: "Stephen Johnston" <>
To: <>
Sent: Friday, April 07, 2006 5:34 PM
Subject: st: Econometrically sound to use Mills ratio after mprobit?


I am estimating a multinomial probit for a selection equation with 3 choices and I am interested in using the inverse mills ratio generated from the MNP in a second step equation. I know how to implement this procedure, however, I have not been able to find any literature that proves that the Heckman two-step estimation procedure can appropriately and directly extend from a probit selection equation to a multinomial probit selection equation. Does anyone know of any papers that address this issue?

* For searches and help try:

*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index