Actually, robust standard errors for logit and some other models (glm
family) are available. The basic option is robust=TRUE, but there are
other options as well.
http://gking.harvard.edu/zelig/docs/Additional_Inputs7.html
also see demo(robust)
Kosuke
-----------------------------------------------------
Kosuke Imai Office: Corwin Hall 041
Assistant Professor Phone: 609-258-6601
Department of Politics eFax: 973-556-1929
Princeton University Email: kimai(a)Princeton.Edu
Princeton, NJ 08544-1012 http://imai.princeton.edu
-----------------------------------------------------
On Thu, 31 May 2007, Olivia Lau wrote:
> Dear Xavier,
>
> I'm actually not in charge of robust standard errors; I am cc'ing my
> coauthor Kosuke who implemented them.
>
> Best,
> Olivia Lau
>
> On 5/31/07, Xavier Fernández i Marín <xavier.fernandez(a)upf.edu> wrote:
>> Hello Olivia,
>>
>> I've been an R user for long time and I'm starting to discover Zelig and
>> its abilities.
>>
>> I have tried to build a logit model with robust errors and clusters for one
>> variable, but according to the mailing list this feature hasn't been (yet)
>> released (or it wasn't in october 2006):
>> http://lists.hmdc.harvard.edu/lists/zelig/2006_10/msg00001.html
>>
>> My question is about the availability of this feature. Is it on the list of
>> features to include? Any idea about the possible periodicity? The questions
>> are just to have an idea and whether I would have to wait or program it for
>> myself. So in any case it pretends to be a "demand".
>>
>> Since from the mailing list you seemed to be the programmer dedicated to
>> this functions I have sent the email directly to you.
>>
>>
>> Thank you very much for all your work.
>>
>>
>> Best regards,
>>
>> --
>> Xavier Fernández i Marín
>>
>> xavier.fernandez(a)upf.edu
>> http://giptsi.upf.edu/xavier/
>>
>>
>
Hi, everyone.
Thanks for your patience, and for reporting the bugs. Keep the
reports coming -- we rely on users to find inventive ways to use Zelig
and R, and suggest improvements.
I've just rolled up a new version (2.8-3) of Zelig that's compatible
with R 2.5.0, and fixed the bugs kindly identified by Brant, Javier,
and Andrew. It's available for download from the Zelig website using
(within R):
> install.packages("Zelig", repos = "http://gking.harvard.edu")
and should be available from CRAN in a day or two.
If you are using R 2.4.0, consider upgrading at least to R 2.4.1. If
you are using R 2.4.1 and can't get the new version using
install.packages(), you can download it manually from
http://gking.harvard.edu/bin/windows/contrib/2.5/Zelig_2.8-3.zip, then
use the drop down menus in R to install it.
Yours,
Olivia
p.s. -- Zelig doesn't current support cox proportional hazard models,
but we're working on that too.
On 5/29/07, Inman, Brant A. M.D. <Inman.Brant(a)mayo.edu> wrote:
>
> Hi Zelig helpers. I have two brief questions/points.
>
> 1) Does Zelig support Cox regression models?
>
> 2) I get the following error message when I try to answer the question
> above using R 2.5's help system:
>
> > help.zelig("models")
> Error: 'file_test' is not an exported object from 'namespace:tools'
> >
>
> Brant
>
> _________________________________________________________
> Dr. Brant A. Inman, MD FRCSC
> Urologic Oncology Fellow, Mayo Clinic College of Medicine
> 200 First Street SW
> Rochester, MN 55905
> Phone: (507) 284-3016
> Fax: (507) 284-4951
> Email: inman.brant(a)mayo.edu
> _________________________________________________________
>
> -
> Zelig Mailing List, served by Harvard-MIT Data Center
> Send messages: zelig(a)lists.gking.harvard.edu
> [un]subscribe Options: http://lists.gking.harvard.edu/?info=zelig
> Zelig program information: http://gking.harvard.edu/zelig/
>
>
-
Zelig Mailing List, served by Harvard-MIT Data Center
Send messages: zelig(a)lists.gking.harvard.edu
[un]subscribe Options: http://lists.gking.harvard.edu/?info=zelig
Zelig program information: http://gking.harvard.edu/zelig/
Hi Zelig helpers. I have two brief questions/points.
1) Does Zelig support Cox regression models?
2) I get the following error message when I try to answer the question
above using R 2.5's help system:
> help.zelig("models")
Error: 'file_test' is not an exported object from 'namespace:tools'
>
Brant
_________________________________________________________
Dr. Brant A. Inman, MD FRCSC
Urologic Oncology Fellow, Mayo Clinic College of Medicine
200 First Street SW
Rochester, MN 55905
Phone: (507) 284-3016
Fax: (507) 284-4951
Email: inman.brant(a)mayo.edu
_________________________________________________________
-
Zelig Mailing List, served by Harvard-MIT Data Center
Send messages: zelig(a)lists.gking.harvard.edu
[un]subscribe Options: http://lists.gking.harvard.edu/?info=zelig
Zelig program information: http://gking.harvard.edu/zelig/
try to see what elements are in the summary object by
tmp <- summary(il6w.out)
names(tmp)
then you can extract each element by
tmp$xxx
where xxx is the name of the element.
Kosuke
-----------------------------------------------------
Kosuke Imai Office: Corwin Hall 041
Assistant Professor Phone: 609-258-6601
Department of Politics eFax: 973-556-1929
Princeton University Email: kimai(a)Princeton.Edu
Princeton, NJ 08544-1012 http://imai.princeton.edu
-----------------------------------------------------
On Fri, 25 May 2007, Abdus Sattar wrote:
> Hello:
>
> I have the following R output from the zelig for fitting a tobit model:
>
>> summary(il6w.out)
> Call:
> zelig(formula = il6.data$il6 ~ il6.data$apache, model = "tobit",
> data = il6.data, robust = TRUE, cluster = "il6.data$subject",
> weights = il6.data$w)
> Value Std. Err (Naive SE) z p
> (Intercept) 4.572 0.12421 0.27946 36.8 1.44e-296
> il6.data$apache 0.983 0.00189 0.00494 519.4 0.00e+00
> Log(scale) 2.731 0.00660 0.00477 414.0 0.00e+00
> Scale= 15.3
> Gaussian distribution
> Loglik(model)= -97576 Loglik(intercept only)= -108964
> Chisq= 22777 on 1 degrees of freedom, p= 0
> (Loglikelihood assumes independent observations)
> Number of Newton-Raphson Iterations: 6
> n=5820 (1180 observations deleted due to missingness)
>
>
>
> After the fitting the above Tobit model using zelig, if I use the following command then I can get the regression coefficents:
>
> beta=coefficients(il6.out)
>> beta
> (Intercept) il6.data$apache
> 4.572 0.983
>
>
> How may I extract the "Naive SE" from the following output please?
>
> I would appreciate if any help you could provide me in this regard please. Thank you.
>
> Sattar
>
>
>
> ____________________________________________________________________________________Yahoo! oneSearch: Finally, mobile search
> that gives answers, not web links.
> http://mobile.yahoo.com/mobileweb/onesearch?refer=1ONXIC
-
Zelig Mailing List, served by Harvard-MIT Data Center
Send messages: zelig(a)lists.gking.harvard.edu
[un]subscribe Options: http://lists.gking.harvard.edu/?info=zelig
Zelig program information: http://gking.harvard.edu/zelig/
Hi,
I have problems with summary() on multiply-imputed mlogit objects. The
error is:
Error in apply(coef, 1, mean) : dim(X) must have a positive length
I noted that Christopher Lawrence detected this error before, and I
thought that the problem was resolved in version 2.7-5. Is this correct?
Otherwise, how can I apply the patch posted by Christopher?
http://lists.hmdc.harvard.edu/lists/zelig/2006_12/msg00001.html
Kind regards
Javier Márquez
Hi all,
This is something that I would like to see happen. Bayesm code is quite extensive. Already you have integrated MCMC methods into some of your modelling.
This would make my life a great deal easier
Thanks Paul