Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: st: Interpreting Conditional Marginal effects after Heckman
From
Austin Nichols <austinnichols@gmail.com>
To
statalist@hsphsun2.harvard.edu
Subject
Re: st: st: Interpreting Conditional Marginal effects after Heckman
Date
Mon, 4 Jun 2012 14:04:40 -0400
Clifton Chow <clifton_chow@post.harvard.edu>:
Or, better, for a dummy RHS var, 10.3 percent:
di exp(1+.098)/exp(1)
On Mon, Jun 4, 2012 at 1:55 PM, Austin Nichols <austinnichols@gmail.com> wrote:
> Clifton Chow <clifton_chow@post.harvard.edu>
> No, 9.8 percent higher.
>
> Note that this is very far from being interpretable as a causal
> relationship; no doubt causation goes both ways and there are many
> omitted variables.
>
> On Sat, Jun 2, 2012 at 11:39 AM, Clifton Chow
> <clifton_chow@post.harvard.edu> wrote:
>> Dear Statalist,
>>
>> After combing through the archives of the listserv extensively I managed to estimate a log(hourly wage) model with correction for selection and retrieve conditional marginal effects. I am wondering if I can interpreting the MEs in dollar terms? As an example, one of my significant conditional ME coefficients from a binary variable called "Engaging in Social Activities" is 0.098. Could I interpret this as conditioned on those whose wages are observed, for those engaging in social activities, their predicted hourly wage is .09 cents (almost 10 cents) higher than those who do not?
>>
>> Thanks in advance as usual.
>> C.
*
* 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/