Statalist The Stata Listserver


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: helped with fixed effects logit


From   Michael Horowitz <horowitz@fas.harvard.edu>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: helped with fixed effects logit
Date   Tue, 7 Mar 2006 14:35:38 -0500 (EST)

Thank you for the helpful suggestion.  Let me rephrase.  DemocstateA is
the democracy status of State A.  DemocstateB is the democracy status of
State B.  So they can be very different.  They will be measured for a
given country in a given observation for the same year for each country,
the year of the crisis.  So I am not sure your fix still applies.  Does
it?  Actually it still might. . .what do you think?

I have considered the exogenous nature of democracy, etc.  I am doing this
at the request of someone else that wants to see the results like this. .

Michael

On Tue, 7 Mar 2006, Austin Nichols wrote:

> Not my field, but I think you should have two observations on each
> crisis, one for each country--otherwise you are constraining the
> effect of democstateA and democstateB to be the same when they
> represent different countries, right?  I mean, if Sudan is country A
> one time and country B another time, then Sudan is making a
> contribution to both coefficients, and which one they contribute to in
> which year is arbitrary, right?  Once you -reshape democstate,
> i(crisis_id) j(state) str- you can
>
> clogit DV democ controls, group(country_id)
>
> I guess--but have you considered whether democstate is exogenous to
> crisis behavior?  Especially in the fixed-effects formulation, where
> you are identifying the effect off changes in status, from democracy
> to not, or from not democ to democ, I would guess that crises can
> cause democ status at least as much as vice versa.  Not to name any
> names or dates.
>
> On 3/7/06, Michael Horowitz <horowitz@fas.harvard.edu> wrote:
> > To whom it may concern:
> >
> > I have a paper where I am examining the impact of democracy on crisis
> > behavior.  I need to estimate a fixed effects or conditional logit model
> > but I am not sure how.
> >
> > The data is set up dyadically, meaning each observation has data on the
> > crisis and data for state A in the crisis and state B in the crisis
> >
> > Here is the functional form of the logistic regression I have run
> >
> > logit DV democstateA democstateB control1 control2 control3 control4
> >
> > I need to estimate a fixed effects model to control for the impact of
> > specific countries.  I know that I need to use conditional logit to
> > control for unmeasured heterogeneity.
> >
> > But I am not sure how to do it.  Specifically, in the clogit setup, it
> > should look like:
> >
> > clogit DV democstateA democstateB control1 control2 control3 control4,
> > group(????).
> >
> > What I am unclear about is what goes in the parentheses.  If anyone could
> > assist, I would very much appreciate it.  I apologize for asking such a
> > basic question.
> >
> > Regards,
> > Michael Horowitz
> > *
> > *   For searches and help try:
> > *   http://www.stata.com/support/faqs/res/findit.html
> > *   http://www.stata.com/support/statalist/faq
> > *   http://www.ats.ucla.edu/stat/stata/
> >
>
> *
> *   For searches and help try:
> *   http://www.stata.com/support/faqs/res/findit.html
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
>

*******************************************************************************

Michael Horowitz
83 Beacon St., Apt. 3
Somerville, MA 02143
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2020 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index