Statalist


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

Re: st: weird margins


From   Rich Steinberg <[email protected]>
To   [email protected]
Subject   Re: st: weird margins
Date   Fri, 02 Oct 2009 14:26:02 -0400

You are entirely right.  My embarrassed thanks.

Austin Nichols wrote:
Just guessing, but do you mean
 predict(ystar(0,.))
instead of
 predict(ystar(o,.))
?

On Thu, Oct 1, 2009 at 3:31 PM, Rich Steinberg <[email protected]> wrote:
I run a tobit because of left censoring at zero, then want to use margins to
predict the marginal slope for the observable dependent variable atotgiv.

Everything looks ok except in the output appears
Expression: E(atotgiv*|atotgiv>otherrelh), predict (ystar(0,.))

The appearance of otherrelh in this expression is mysterious.  This is
another dummy variable used as a control.  I didn't program it to look at
that, and I think it should read, instead, E(atotgiv*|atotgiv>0), etc.

Is this a bug?  A mistake on my part?  A misunderstanding?

Here is the exact command and headers for the results:

margins, predict(ystar(o,.)) dydx( earn01 assety01 welfare01 nonwelfare01
annuapprecinh annuownwealthn annuheq )

Average marginal effects                          Number of obs   =
4935
Model VCE    : Robust

Expression   : E(atotgiv*|atotgiv>otherrelh), predict(ystar(o,.))
dy/dx w.r.t. : earn01 assety01 welfare01 nonwelfare01 annuapprecinh
             annuownwealthn annuheq

--

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/

--
Rich Steinberg
Department of Economics, 516 Cavanaugh Hall
IUPUI
Indianapolis, IN 46202-5140
317-278-7221

"Unanswered email since 1955"

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index