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: Question about average marginal effects for logit models with dummy variables
From
Richard Williams <[email protected]>
To
[email protected], [email protected]
Subject
Re: st: Question about average marginal effects for logit models with dummy variables
Date
Mon, 08 Oct 2012 07:14:37 -0500
At 05:45 AM 10/8/2012, Tirthankar Chakravarty wrote:
-margins- inherits whether variables are discrete or continuous from
the estimation command that precedes it (in your case -logit-). In
turn, the estimation command does its best to gauge whether included
variables are discrete or continuous.
The part about the estimation command isn't quite right. Even if a
variable is coded 0/1 margins will treat it as continuous unless you
use factor variable notation. As Nick Cox explained once, margins
needs to know if a variable is discrete, as opposed to, say, being a
continuous variable that only happens to take on the values of 0 and
1 in the sample.
To change the default behaviour, or indeed to be cautious, it is
advisable to use the unary operators to denote continuous and
indicator variables, "c." and "i." (as documented in -help fvvarlist-)
liberally.
Again, in the absence of any factor variable notation, the default
behavior of margins is to assume variables are continuous. mfx, on
the other hand, would assume a variable coded 0/1 was discrete. It is
more than just being cautious -- margins won't handle discrete
variables correctly if you are not using factor variable notation. If
x1 is coded 0/1, the estimation command won't care if you refer to it
as x1 or i.x1, but margins will.
The documentation for the -margins- command goes into great details on
these matters (-help margins-).
T
On Mon, Oct 8, 2012 at 3:41 PM, Bob Reed <[email protected]> wrote:
> Hi, When Stata calculates AMEs for logit models with dummy
variables, does it "know" that the dummy variable is discrete, and
calculate its marginal effect accordingly?
>
> Bob Reed
>
> --------------------------------------------------------------------
> W. Robert Reed
> Professor and Head of Department
> Department of Economics and Finance
> University of Canterbury
> Private Bag 4800
> Christchurch
> New Zealand
> Phone: +64-3-3642846
> Fax: +64-3-3642635
> Email: [email protected]
> Homepage: http://www.econ.canterbury.ac.nz/personal_pages/bob_reed/
>
> Replications Co-Editor, Public Finance Review
> http://www.sagepub.com/journalsProdEditBoards.nav?prodId=Journal200768
> --------------------------------------------------------------------
> The curious task of economics is to demonstrate to men how little
they really know about what they imagine they can design. - F.A. Hayek
>
>
>
> This email may be confidential and subject to legal privilege, it may
> not reflect the views of the University of Canterbury, and it is not
> guaranteed to be virus free. If you are not an intended recipient,
> please notify the sender immediately and erase all copies of the message
> and any attachments.
>
> Please refer to http://www.canterbury.ac.nz/emaildisclaimer for more
> information.
>
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/faqs/resources/statalist-faq/
> * http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/
-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME: (574)289-5227
EMAIL: [email protected]
WWW: http://www.nd.edu/~rwilliam
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/