Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: Re: what is the difference between '.psel' and '.xbs' for heckman postestimation

From   jing liu <>
Subject   st: Re: what is the difference between '.psel' and '.xbs' for heckman postestimation
Date   Tue, 20 Apr 2010 12:17:54 +0200

> Hi,
> I am using heckman regression to calculate the selection effect of wage.
> first of all, I am not sure if I shall use the 'twostep' model here or not.
> I sort of know it is related to how to identify the selection effect, but I
> am totally confused with the instruction of 'twostep'.
>     here is the link:
> secondly, I want to  interprete the coefficients. So after run 'heckman'
> command, I should use 'predict' command. For stata 8 it was 'predict
> varname. xbs'. The 'xbs' is used to generate the probability that an
> observation will be selected or selection probability. But there is a 'psel'
> subcommand talking about the same thing in Stata11. So now I don't know
> which one i should choose, and what is the difference between the 'xbs' and
> 'psel' now.
>     what stata11 says:
>         xbs: linear prediction for selection equation
>         psel: calculates the probability of selection (or being observed)
>     the link for this is:
> thirdly, it was possible to use the following code to calculate inverse
> mills ratio (gen testpr = normden(selxbpr)/norm(selxbpr)), now we are able
> to use subcommand (mills) to do the same thing, but the command (normden and
> norm) doesn't not exist any more. are they changed? and what are they now?
> forthly,  it says twostep doesn't work with any weight subcommand in heckman
> regression. But I run my heckman with both twostep and pweight/iweight. They
> both work.
>       Stata11 says: pweights, aweights, fweights, and iweights are allowed
> with maximum likelihood estimation; see weight.  No weights are allowed if
> twostep
>       is specified.
> by the way, i have already subscribed my stata11 on line with this email.
> but if you need my serial no. please contact me.
> thanks a lot

刘京   Jing LIU

*   For searches and help try:

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index