[R-sig-Geo] R squared in lagsarlm

Roger Bivand Roger@B|v@nd @end|ng |rom nhh@no
Thu Mar 21 14:28:59 CET 2019


Do not post HTML-mail!

What do you mean by: "what parameters of SAR we should expose"? What do 
you mean by SAR? Do you mean the SAR model (simultaneous autoregressive 
model, a.k.a. the simultaneous spatial error model) or the SAR model 
(spatial autoregressive model a.k.a. the simultaneous spatial lag model)? 
If the spatial lag model, only ever report impacts, never report the 
betas. Please be more precise.

Roger

On Thu, 21 Mar 2019, Leonardo Matheus Servino wrote:

> Thanks, and one more question: what parameters of SAR we should expose in
> articles?
>
> <https://www.avast.com/sig-email?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=webmail>
> Livre
> de vírus. www.avast.com
> <https://www.avast.com/sig-email?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=webmail>.
> <#DAB4FAD8-2DD7-40BB-A1B8-4E2AA1F9FDF2>
>
> Em qui, 21 de mar de 2019 às 10:09, Roger Bivand <Roger.Bivand using nhh.no>
> escreveu:
>
>> The Nagelkerke measure is optionally provided in the summary method:
>> Nagelkerke NJD (1991) A note on a general definition of the coefficient of
>> determination. Biometrika 78: 691-692.
>>
>> See https://r-spatial.github.io/spdep/reference/summary.sarlm.html or
>> ?summary.sarlm.
>>
>> There is no "R squared" for these models, the likelihood ratio is a better
>> comparative measure.
>>
>> Roger
>>
>> On Wed, 20 Mar 2019, Leonardo Matheus Servino wrote:
>>
>>> Hello,
>>>
>>> I would like to know where I can find the Rsquared value in lagsarlm
>>>
>>> Thanks
>>>
>>>
>>
>> --
>> Roger Bivand
>> Department of Economics, Norwegian School of Economics,
>> Helleveien 30, N-5045 Bergen, Norway.
>> voice: +47 55 95 93 55; e-mail: Roger.Bivand using nhh.no
>> https://orcid.org/0000-0003-2392-6140
>> https://scholar.google.no/citations?user=AWeghB0AAAAJ&hl=en
>>
>
>
>

-- 
Roger Bivand
Department of Economics, Norwegian School of Economics,
Helleveien 30, N-5045 Bergen, Norway.
voice: +47 55 95 93 55; e-mail: Roger.Bivand using nhh.no
https://orcid.org/0000-0003-2392-6140
https://scholar.google.no/citations?user=AWeghB0AAAAJ&hl=en


More information about the R-sig-Geo mailing list