Statalist The Stata Listserver


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

Re: st: Unobserved heterogeneity in logistic regression


From   "Cristina Pereira" <cristina.pereira@fea-evora.com.pt>
To   <statalist@hsphsun2.harvard.edu>
Subject   Re: st: Unobserved heterogeneity in logistic regression
Date   Tue, 31 Jan 2006 14:40:36 -0000

logit clforum idade  fem habmen9 habsup resid  vexpFEA voutras exp formtem s
> emin melodea cinea roteiros  pateo clasexp expecta inform acolhim

Iteration 0:   log likelihood = -64.481718
Iteration 1:   log likelihood = -45.955808
Iteration 2:   log likelihood = -43.036576
Iteration 3:   log likelihood = -42.699927
Iteration 4:   log likelihood = -42.687686
Iteration 5:   log likelihood =  -42.68766

Logit estimates                                   Number of obs   =
134
                                                   LR chi2(18)     =
43.59
                                                   Prob > chi2     =
0.0007
Log likelihood =  -42.68766                       Pseudo R2       =
0.3380

------------------------------------------------------------------------------
  clforum |      Coef.   Std. Err.       z     P>|z|       [95% Conf.
Interval]
---------+--------------------------------------------------------------------
    idade |  -.0379192   .0237848     -1.594   0.111      -.0845364
.0086981
      fem |    .142543   .5963118      0.239   0.811      -1.026207
1.311293
  habmen9 |   -.361584    .904894     -0.400   0.689      -2.135144
1.411976
   habsup |  -1.911038   .9093529     -2.102
0.036      -3.693337   -.1287392
    resid |  -1.386813   .8617904     -1.609   0.108      -3.075891
.3022655
  vexpFEA |   1.170202   .7630049      1.534   0.125      -.3252598
2.665665
  voutras |   .5517524   .7542407      0.732   0.464      -.9265323
2.030037
      exp |  -.8654879   .9781649     -0.885   0.376      -2.782656
1.05168
  formtem |   .6785345   .8420722      0.806   0.420      -.9718967
2.328966
    semin |   .3446929      .7274      0.474   0.636      -1.080985
1.770371
  melodea |   1.178986   .9043637      1.304   0.192      -.5935341
2.951506
    cinea |  -.6163336   .8959065     -0.688   0.491      -2.372278
1.139611
roteiros |   .8907071   1.090565      0.817   0.414      -1.246761
3.028175
    pateo |   .6254803   .9519656      0.657   0.511      -1.240338
2.491299
  clasexp |   .9305477   .3527112      2.638   0.008       .2392466
1.621849
  expecta |  -1.105424   1.171044     -0.944   0.345      -3.400628
1.18978
   inform |   1.191919   .8563612      1.392   0.164      -.4865177
2.870356
  acolhim |   1.975343   1.194611      1.654   0.098       -.366051
4.316737
    _cons |   -1.70797   1.870524     -0.913   0.361      -5.374129
1.958189
------------------------------------------------------------------------------
With an output like this how do i calculate the probabilitys from chi
square to interpretate the coeficients?

----- Original Message -----
From: "daniel waxman" <dan@amplecat.com>
To: <statalist@hsphsun2.harvard.edu>
Sent: Monday, January 30, 2006 11:55 PM
Subject: RE: st: Unobserved heterogeneity in logistic regression


> Thanks for the response.  As it turns out, things are quite consistent
> between hospitals, and between everything else... perhaps I am just being
> paranoid.
>
> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu
> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Karen Norberg
> Sent: Monday, January 30, 2006 2:48 PM
> To: statalist@hsphsun2.harvard.edu
> Subject: Re: st: Unobserved heterogeneity in logistic regression
>
> Depending on the kind of heterogeneity you think might exist, one option
> is to use a 'fixed effects' or conditional logistic model. If you think
> there is unobserved heterogeneity between hospitals, you stratify the
> sample by hospital, thus 'conditioning out' of your model any
> characteristics that may vary between hospitals, but remain constant among
> observations within hospital.
>
> Hospital isn't the only thing you could condition on - you could use
> month or year fixed effects, other attributes -
>
> Karen Norberg, MD
>
>
>
> On Mon, 30 Jan 2006, Maarten buis wrote:
>
>> Dear Daniel:
>>
>> The problem with unobserved heterogeneity is that it is well...
> unobserved. Apparently you have
>> many predictors of mortality available, so an obvious solution is to add
> some of these predictors.
>> In an earlier post you suggested that your variables are collinear, so
>> you
> probably don't want to
>> add them all. That is no problem since the fact that they are collinear
> with the variables left
>> out means that most of the variance is captured by the variables in the
> model (it does make the
>> causal interpretation of these control variables more difficult, but the
> roll of control variables
>> is to control, and that is what they do).
>>
>> I see the results of my models more as a rough indication than anything
> else. So I tend to worry
>> less about technicalities like these.  In my own research I deal with
> survey data, and in my
>> department they tape trained and experienced interviewers from reputable
> agencies while they are
>> interviewing and code the interactions between interviewer and
> interviewed. The results make me
>> very skeptical about the precision of my data. (See aside below) The
>> paper
> was written more to
>> satisfy my nerdish tendencies than that I thought that the impact of this
> phenomenon would be
>> large enough to be noticeable above the random noise coming from data
> collection. (I may be wrong
>> though; the simulations by Glenn Hoetker seem to point in that direction,
> though I have not yet
>> read it as carefully as I should). I pointed you to this phenomenon
> because in such a sensitivity
>> analysis this phenomenon might be worthy of a footnote, and my working
> paper might be helpful in
>> understanding the literature to which it refers (and also the literature
> to which Richard Williams
>> referred).
>>
>> So, my not entirely satisfactory answer is: dealing with "observed
> heterogeneity" is much easier
>> than unobserved heterogeneity. If you use additional modeling on top of
> that and you get different
>> results make sure you understand why that is the case and convince
> yourself that that is
>> plausible.
>>
>> HTH,
>> Maarten
>>
>> Aside
>> Taping interviews does result in some funny interactions though:
> Interviewer: How many times do
>> you eat grain products for breakfast? Respondent: Well.... never ....
> eh.... well no, that's not
>> right, beer is a grain product too, isn't it?
>>
>> More often the interactions aren't that funny. For instance, the
> "experienced" interviewer looks
>> around the room and decides for the respondent in which income and
> educational category he/she
>> falls, or asks very suggestive questions, makes mistakes while entering
> the data, etc. etc. etc.
>>
>> --- daniel waxman <dan@amplecat.com> wrote:
>>
>>> Maartin Buis directed me to a short paper of his:  "Unobserved
> heterogeneity
>>> in logistic regression":
>>>
>>> http://home.fsw.vu.nl/m.buis/
>>>
>>> The concept makes sense--the question is what to do about it.
>>
>> <snip>
>>
>>> There are of course many unobserved causes for in-hospital mortality,
> but
>>> insofar as this particular model seems to work, do I need to deal with
> this?
>>> If one does try to deal with it in a situation such as mine, is it a
> matter
>>> of using a method other than simple logistic regression to fit the
> model, or
>>> is it more a matter of assessment of goodness if fit?
>>>
>>
>>
>> -----------------------------------------
>> Maarten L. Buis
>> Department of Social Research Methodology
>> Vrije Universiteit Amsterdam
>> Boelelaan 1081
>> 1081 HV Amsterdam
>> The Netherlands
>>
>> visiting adress:
>> Buitenveldertselaan 3 (Metropolitan), room Z214
>>
>> +31 20 5986715
>>
>> http://home.fsw.vu.nl/m.buis/
>> -----------------------------------------
>>
>>
>>
>> ___________________________________________________________
>> Yahoo! Photos - NEW, now offering a quality print service from just 8p a
> photo http://uk.photos.yahoo.com
>> *
>> *   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/
>
>
> *
> *   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/



© Copyright 1996–2021 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index