standard errors of total impacts in a spatial lag regression model lagsarlm

[Rafael Pereira]

Dear all,

I am using a spatial lag regression model in a paper. I know already how to
get the total impacts of the model, but I don't know how to generate the
standard errors of the total impacts.

In this paper by Roger Bivand here*, these SE were "calculated using the
'estimable' function in the R gmodels package." I've checked the function
documentation but I couldn't really get my head around how to use it on
a lagsarlm lag model.

Can someone give me hand? There is a reproducible example below, but if any
of you could share a snippet of code you have already used this would be
very helpful already.

# reproducible example
data(oldcol)
COL.lag.eig <- lagsarlm(CRIME ~ INC + HOVAL, data=COL.OLD, type="lag",
                        nb2listw(COL.nb, style="W"), method="eigen",
quiet=FALSE)
summary(COL.lag.eig, correlation=TRUE)



* http://openjournals.wu.ac.at/region/paper_107/107.html

best wishes,

Rafael H M Pereira

        [[alternative HTML version deleted]]

_______________________________________________
R-sig-Geo mailing list
[hidden email]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo

[Roger Bivand]

On Wed, 3 Jan 2018, Rafael Pereira wrote:

> Dear all,
>
> I am using a spatial lag regression model in a paper. I know already how to
> get the total impacts of the model, but I don't know how to generate the
> standard errors of the total impacts.
>
> In this paper by Roger Bivand here*, these SE were "calculated using the
> 'estimable' function in the R gmodels package." I've checked the function
> documentation but I couldn't really get my head around how to use it on
> a lagsarlm lag model.

Wrong reference - those are for SLX and SDEM models, but use the
appropriate impacts() methods. See ?impacts. Remember to create a vector
of traces, and help your head by (re)-reading LeSage & Pace 2009, and
https://www.jstatsoft.org/index.php/jss/article/view/v063i18, p. 8 and
section 5.

Hope this helps,

Roger

>
> Can someone give me hand? There is a reproducible example below, but if any
> of you could share a snippet of code you have already used this would be
> very helpful already.
>
> # reproducible example
> data(oldcol)
> COL.lag.eig <- lagsarlm(CRIME ~ INC + HOVAL, data=COL.OLD, type="lag",
>                        nb2listw(COL.nb, style="W"), method="eigen",
> quiet=FALSE)
> summary(COL.lag.eig, correlation=TRUE)
>
>
>
> * http://openjournals.wu.ac.at/region/paper_107/107.html
>
> best wishes,
>
> Rafael H M Pereira
>
> [[alternative HTML version deleted]]
>
> _______________________________________________
> R-sig-Geo mailing list
> [hidden email]
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>

--
Roger Bivand
Department of Economics, Norwegian School of Economics,
Helleveien 30, N-5045 Bergen, Norway.
voice: [phone]; e-mail: [hidden email]
Editor-in-Chief of The R Journal, https://journal.r-project.org/index.html
http://orcid.org/0000-0003-2392-6140
https://scholar.google.no/citations?user=AWeghB0AAAAJ&hl=en

_______________________________________________
R-sig-Geo mailing list
[hidden email]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo

[Rafael Pereira]

Thank you, Roger!

I will look into this .

best wishes,

Rafael H M Pereira

On Wed, Jan 3, 2018 at 10:32 AM, Roger Bivand <[hidden email]> wrote:

> On Wed, 3 Jan 2018, Rafael Pereira wrote:
>
> Dear all,
>>
>> I am using a spatial lag regression model in a paper. I know already how
>> to
>> get the total impacts of the model, but I don't know how to generate the
>> standard errors of the total impacts.
>>
>> In this paper by Roger Bivand here*, these SE were "calculated using the
>> 'estimable' function in the R gmodels package." I've checked the function
>> documentation but I couldn't really get my head around how to use it on
>> a lagsarlm lag model.
>>
>
> Wrong reference - those are for SLX and SDEM models, but use the
> appropriate impacts() methods. See ?impacts. Remember to create a vector of
> traces, and help your head by (re)-reading LeSage & Pace 2009, and
> https://www.jstatsoft.org/index.php/jss/article/view/v063i18, p. 8 and
> section 5.
>
> Hope this helps,
>
> Roger
>
>
>> Can someone give me hand? There is a reproducible example below, but if
>> any
>> of you could share a snippet of code you have already used this would be
>> very helpful already.
>>
>> # reproducible example
>> data(oldcol)
>> COL.lag.eig <- lagsarlm(CRIME ~ INC + HOVAL, data=COL.OLD, type="lag",
>>                        nb2listw(COL.nb, style="W"), method="eigen",
>> quiet=FALSE)
>> summary(COL.lag.eig, correlation=TRUE)
>>
>>
>>
>> * http://openjournals.wu.ac.at/region/paper_107/107.html
>>
>> best wishes,
>>
>> Rafael H M Pereira
>>
>>         [[alternative HTML version deleted]]
>>
>> _______________________________________________
>> R-sig-Geo mailing list
>> [hidden email]
>> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>>
>>
> --
> Roger Bivand
> Department of Economics, Norwegian School of Economics,
> Helleveien 30, N-5045 Bergen, Norway.
> voice: [phone]; e-mail: [hidden email]
> Editor-in-Chief of The R Journal, https://journal.r-project.org/index.html
> http://orcid.org/0000-0003-2392-6140
> https://scholar.google.no/citations?user=AWeghB0AAAAJ&hl=en
>

        [[alternative HTML version deleted]]

_______________________________________________
R-sig-Geo mailing list
[hidden email]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo