[R-sig-Geo] "Islands" in spatial (area) analysis

[Roger Bivand]

Wolfgang,

I think that you were more interested in the consequences of missing 
neighbours for the analysis of areal data. I did look at this 15 years 
ago with Boris Portnov, in the context of ESDA:

@incollection{bivand+portnov:04,
   author = {R. S. Bivand and B. A. Portnov},
   editor = {L. Anselin and R. J. G. M. Florax and S. J. Rey},
   title = {Exploring spatial data analysis techniques using {\RR}: the 
case of observations with no neighbours},
   booktitle = {Advances in Spatial Econometrics: Methodology, Tools, 
Applications},
   year = {2004},
   publisher = {Springer},
   address = {Berlin},
   pages = {121--142}
}

There are oddities in the Moran scatterplot, and also in mapping the 
graph-based neighbour representation into matrix form, say with the 
spatial lag of a no-neighbour observation's value being zero (for 
zero.policy=TRUE). That paper was the basis for the zero.policy= 
framework. There are other consequences that you've found with respect to 
the number of subgraphs, which may or may not break formal assumptions of 
analysis methods. In addition, we don't know how far the broken 
assumptions actually matter. This would probably be a good candidate for 
proper study including simulation.

Best wishes,

Roger

On Mon, 22 Aug 2016, chris english wrote:

> Wolfgang,
>
> The lake on the island in the bigger lake is a topological construct, and I
> believe was covered by Bivand et al (1st ed.) A search of 'topology island
> hole' or 'topology island hole GIS analysis' will get you out of the
> Caribbean and into some serious papars. 'Gdal island hole' will direct
> toward how things are generally handled in R.
>
> Cheers,
>
> Chris
>
> On Thu, Aug 18, 2016 at 4:47 PM, Ludwig-Mayerhofer, Wolfgang, Prof. Dr. <
> ludwig-mayerhofer at soziologie.uni-siegen.de> wrote:
>
>> Dear all,
>>
>> I'm new to this list, and regrettably I have to  introduce myself with a
>> question which is not necessarily related to R, even though any R-related
>> answer will also help (as I do my spatial analyses mostly with R).
>>
>> My question is simply: Does anybody know a good (possibly
>> systematic/comprehensive/dedicated/exhaustive) text about the
>> role/problem of "islands", i.e. areas without neighbors, in (area data)
>> spatial analysis? I know that some procedures don't run in the presence of
>> islands, but others do (with the appropriate zero policies), but I'm not
>> always sure whether this means that the results are really meaningful.
>>
>> I can only occasionally find reference to the "island" problem in the
>> literature (many texts, among which are VERY good texts like those by
>> Bivand et al or Banerjee et al, seem to ignore it entirely), and what
>> little I have found is very superficial (aside remarks etc.). Regrettably,
>> a search on the Internet (such as "islands spatial analysis") is futile, as
>> all you will get are tons of references to the Caribbean, Canary, tropic,
>> Auckland ... you name it... islands.
>>
>> So any suggestion as to where a more than casual treatment of the topic
>> can be found would be very welcome.
>>
>> Kind regards
>>
>> Wolfgang Ludwig-Mayerhofer
>>
>> ----
>> Prof. Dr. Wolfgang Ludwig-Mayerhofer
>> Universität Siegen/University of Siegen
>> Philosophische Fakultät/Faculty of Arts
>> Adolf-Reichwein-Str. 2
>> 57068 Siegen
>> Germany
>>
>> Wolfgang Ludwig-Mayerhofer (2015): Arbeitsmarktpolitik  aus
>> sozialwissenschaft­licher Sicht: Zur Spannung zwischen "Dekommodifizierung"
>> und "Rekommodifizierung". In: Masuch, Peter et al.  (Hrsg.): Grundlagen und
>> Herausforderungen des Sozialstaats (Band2): Bundessozialgericht und
>> Sozialstaatsforschung. Richterliche Wissensgewinnung und Wissenschaft,
>> Berlin, S. 377-393.
>>
>> Wolfgang Ludwig-Mayerhofer, Olaf Behrend (2015): Enforcing Mobility:
>> Spatial Mobility Under the Regime of Activation, in: Mobilities, 10 (2), S.
>> 326-343. DOI: 10.1080/17450101.2014.898930
>>
>> Wolfgang Ludwig-Mayerhofer (2014): Bildung zwischen Individualisierung und
>> Exklusion. In: Schnei­der, W. und Kraus, W. (Hrsg.): Indivi­du­alisierung
>> und die Legitimation sozialer Ungleich­heit in der reflexiven Moderne.
>> Opladen: Barbara Budrich, S. 167-192
>>
>> Wolfgang Ludwig-Mayerhofer, Uta Liebeskind, Ferdinand Geißler  (2014):
>> Statistik. Eine Einführung für Sozialwissenschaftler, Weinheim: Beltz
>> Juventa, 2014. http://www.beltz.de/produkt_produktdetails/8819-statistik.
>> html
>>
>>
>>         [[alternative HTML version deleted]]
>>
>>
>> _______________________________________________
>> R-sig-Geo mailing list
>> R-sig-Geo at r-project.org
>> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>>
>
> 	[[alternative HTML version deleted]]
>
> _______________________________________________
> R-sig-Geo mailing list
> R-sig-Geo at r-project.org
> 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: +47 55 95 93 55; fax +47 55 95 91 00
e-mail: Roger.Bivand at nhh.no
http://orcid.org/0000-0003-2392-6140
https://scholar.google.no/citations?user=AWeghB0AAAAJ&hl=en
http://depsy.org/person/434412