A complete geo-tyro demonstrating ignorance here: please be tolerant! I have a large dataset comprising the results of a questionnaire from UK respondents. I am interested in geographic variation in responses and have built mixed-effect models incorporating County/Unitary Authority/Local Authority (a level of local government in the UK) as a factor-level random effect in lme4. Extracting the intercept of the random effects I can generate a normalised 0-1 score for each local authority. I would like to illustrate the results of this analysis and generate a map showing LAs coloured using this normalised score to set gray scale. We have campus access to ArcGIS and related programmes but I have no knowledge of these whatsoever and wondered if for this limited task I could work within R? Are there any suitable public domain map objects and how would I go about this? Thank you
Very basic figure question
5 messages · Rob Forsyth, Barry Rowlingson, Paul Hiemstra +2 more
On Thu, Oct 15, 2009 at 11:28 AM, Rob Forsyth
<r.j.forsyth at newcastle.ac.uk> wrote:
A complete geo-tyro demonstrating ignorance here: please be tolerant! I have a large dataset comprising the results of a questionnaire from UK respondents. I am interested in geographic variation in responses and have built mixed-effect models incorporating County/Unitary Authority/Local Authority (a level of local government in the UK) as a factor-level random effect in lme4. Extracting the intercept of the random effects I can generate a normalised 0-1 score for each local authority. I would like to illustrate the results of this analysis and generate a map showing LAs coloured using this normalised score to set gray scale. We have campus access to ArcGIS and related programmes but I have no knowledge of these whatsoever and wondered if for this limited task I could work within R? Are there any suitable public domain map objects and how would I go about this?
You certainly can draw coloured maps in R using the sp package and various other things to help you get the data, such as the rgdal package for reading shapefiles. However, getting the boundary data is another problem... UK boundary data in the public domain? Ooh, I nearly laughed myself off my chair! Are you american? No, UK border data is copyright, controlled, restricted and if you want it you probably end up with an MI5 file. Academics can get access to various boundary data sets via ukborders. but we academics already have MI5 files as dangerous intellectual subversives anyway: http://edina.ac.uk/ukborders/ Barry
Rob Forsyth wrote:
A complete geo-tyro demonstrating ignorance here: please be tolerant! I have a large dataset comprising the results of a questionnaire from UK respondents. I am interested in geographic variation in responses and have built mixed-effect models incorporating County/Unitary Authority/Local Authority (a level of local government in the UK) as a factor-level random effect in lme4. Extracting the intercept of the random effects I can generate a normalised 0-1 score for each local authority. I would like to illustrate the results of this analysis and generate a map showing LAs coloured using this normalised score to set gray scale. We have campus access to ArcGIS and related programmes but I have no knowledge of these whatsoever and wondered if for this limited task I could work within R?
I would rather say that for this limited problem you could use ArcGIS :), for more complex ones use R ;). cheers, Paul
Are there any suitable public domain map objects and how would I go about this? Thank you
_______________________________________________ R-sig-Geo mailing list R-sig-Geo at stat.math.ethz.ch https://stat.ethz.ch/mailman/listinfo/r-sig-geo
Drs. Paul Hiemstra Department of Physical Geography Faculty of Geosciences University of Utrecht Heidelberglaan 2 P.O. Box 80.115 3508 TC Utrecht Phone: +3130 274 3113 Mon-Tue Phone: +3130 253 5773 Wed-Fri http://intamap.geo.uu.nl/~paul
UK boundary data in the public domain? Ooh, I nearly laughed myself
> off my chair! Are you american? No, UK border data is copyright, > controlled, restricted and if you want it you probably end up with an > MI5 file. Academics can get access to various boundary data sets via > ukborders. but we academics already have MI5 files as dangerous > intellectual subversives anyway: > > http://edina.ac.uk/ukborders/ > Hello! Very basic borders can be found here... GADM database of Global Administrative Areas - http://www.gadm.org/ Maybe data found here: http://www.geonames.org could also be helpfull kind regards, Albin
--------------------------------------------------------------------- | Albin Blaschka, Mag. rer.nat - Salzburg, Austria | http://www.albinblaschka.info http://www.thinkanimal.info | It's hard to live in the mountains, hard, but not hopeless!
Hi Rob, You could start with the maps available within R. Here is some text taken from page 88-89 from the ASDAR-book: " It is often attractive to make use of the spatial databases in the maps (comm: and also the mapdata) package. They can be converted to sp class objects using functions such as map2SpatialPolygons in the maptools package. An alternative source of coastlines is the Rgshhs function in maptools, interfacing binary databases of varying resolution distributed by the 'Global Self-consistent, Hierarchical, High-resolution Shoreline Database' project.1212 http://www.soest.hawaii.edu/wessel/gshhs/gshhs.html.4.2 <http://www.soest.hawaii.edu/wessel/gshhs/gshhs.html.4.2> Vector File Formats 89. The best resolution databases are rather large, and so maptools ships only with the coarse resolution one; users can install and use higher resolution databases locally. Figures 2.3 and 2.7, among others in earlier chapters, have been made using these sources." Alternatively you could make use of the maps provided through the FAO (http://www.fao.org/geonetwork/srv/en/main.home <http://www.fao.org/geonetwork/srv/en/main.home> ). Here you can download for example shorelines and a basic map with country borders (but good enough for reference purposes). Henk Henk Sierdsema SOVON Vogelonderzoek Nederland / SOVON Dutch Centre for Field Ornithology Rijksstraatweg 178 6573 DG Beek-Ubbergen The Netherlands tel: +31 (0)24 6848145 fax: +31 (0)24 6848122 -----Oorspronkelijk bericht----- Van: r-sig-geo-bounces at stat.math.ethz.ch [mailto:r-sig-geo-bounces at stat.math.ethz.ch <mailto:r-sig-geo-bounces at stat.math.ethz.ch> ]Namens Rob Forsyth Verzonden: donderdag 15 oktober 2009 12:28 Aan: r-sig-geo at stat.math.ethz.ch Onderwerp: [R-sig-Geo] Very basic figure question A complete geo-tyro demonstrating ignorance here: please be tolerant! I have a large dataset comprising the results of a questionnaire from UK respondents. I am interested in geographic variation in responses and have built mixed-effect models incorporating County/Unitary Authority/Local Authority (a level of local government in the UK) as a factor-level random effect in lme4. Extracting the intercept of the random effects I can generate a normalised 0-1 score for each local authority. I would like to illustrate the results of this analysis and generate a map showing LAs coloured using this normalised score to set gray scale. We have campus access to ArcGIS and related programmes but I have no knowledge of these whatsoever and wondered if for this limited task I could work within R? Are there any suitable public domain map objects and how would I go about this? Thank you _______________________________________________ R-sig-Geo mailing list R-sig-Geo at stat.math.ethz.ch https://stat.ethz.ch/mailman/listinfo/r-sig-geo <https://stat.ethz.ch/mailman/listinfo/r-sig-geo>