[R] Ordinal logistic regression using spatial data

Frank E Harrell Jr feh3k at spamcop.net
Thu Mar 4 03:29:16 CET 2004


On Wed, 3 Mar 2004 18:14:25 -0700
Christof Bigler <christof.bigler at colorado.edu> wrote:

> I have a spatial data set with ordinal response variable containing 
> four levels. I would like to know if and how spatial autocorrelation 
> can be taken into account when ordinal logistic regression is used 
> (e.g. the function lrm from the Design package).
> 
> Thanks for your help!
> Christof

lrm (through the robcov and bootcov functions) can take into account
general intra-cluster correlations.  This works best when clusters do not
contain very many observations.  Different clusters are assumed to be
independent.

---
Frank E Harrell Jr   Professor and Chair           School of Medicine
                     Department of Biostatistics   Vanderbilt University




More information about the R-help mailing list