Hello I'm trying to test for spatial autocorrelation of the residuals of a linear model I fitted. I have a dataset with measurements taken at stations, for which I have the coordinates. I thought using the lm.morantest was a good way of doing this. One needs to specify a listwise object, but I have no idea what is meant by this? Reading some stuff on the web, it appears to me as if you need to create a listwise object from a neighbourhood object? But what is a neighbourhood object? Thanks!! Ellen -- View this message in context: http://r-sig-ecology.471788.n2.nabble.com/lm-morantest-listw-tp7577657.html Sent from the r-sig-ecology mailing list archive at Nabble.com.
lm.morantest: listw?
3 messages · Ellen Pape, Ivailo, Tim Meehan
1 day later
On Tue, Nov 6, 2012 at 12:24 PM, ellenpape <ellen.pape at gmail.com> wrote:
Hello I'm trying to test for spatial autocorrelation of the residuals of a linear model I fitted. I have a dataset with measurements taken at stations, for which I have the coordinates. I thought using the lm.morantest was a good way of doing this. One needs to specify a listwise object, but I have no idea what is meant by this? Reading some stuff on the web, it appears to me as if you need to create a listwise object from a neighbourhood object? But what is a neighbourhood object? Thanks!! Ellen
Dear Ellen, to understand what a neighborhood object is and how to specify one, you could take a look at the excellent tutorial for the spacemakeR package: http://is.gd/ebIPqo HTH, Ivailo -- UBUNTU: a person is a person through other persons.
An embedded and charset-unspecified text was scrubbed... Name: not available URL: <https://stat.ethz.ch/pipermail/r-sig-ecology/attachments/20121107/056e9ad0/attachment.pl>