Bookmark and Share

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: heteroskedasticity and serial correlation in binary choice models


From   Maarten Buis <maartenlbuis@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: heteroskedasticity and serial correlation in binary choice models
Date   Thu, 5 Jan 2012 16:58:04 +0100

On Thu, Jan 5, 2012 at 4:02 PM, A. Berâ wrote:
> Thanks for your replies. From the references you mentioned, I
> understand that the issue dealt with is the comparison of coefficients
> across groups.
>
> I am estimating a model with logit using time series data and I have
> only one continuous independent variable.

Unfortunately, the same problems also apply to a continuous variable
as adding a continuous variable also implies a comparison across
groups, in your case years. All you have done is added an extra
constraint that an extra year will have the same effect regardless of
at which year you start, i.e. the linearity constraint (in the case of
-logit- it is linear in the log(odds), but that does not matter to
this point).

Sorry for not giving better news,
Maarten

--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany


http://www.maartenbuis.nl
--------------------------

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