Continuous geostatistical approach to regression
Hi Terry The function likfit() in the package geoR allows you to do that. You can specifiy a usual regression model in the argument "trend" and the tyope of covariance structure. For an example see the data set "hoef" require(geoR) data(hoef) ?hoef best P.J.
On Mon, 4 Sep 2006, Griffin, Terry W wrote:
I want to perform inferential statistical regressions of spatial data and compare a few methods. I have been working with the techniques to perform the discrete approach to spatial data, i.e. techniques in spdep, spatial econometric, etc., all along and want to broaden the available tools. I would like to perform the continuous approach in addition to the discrete approach, i.e. geostatistical, direct representation, variogram, Cressie's REML, etc. in the same datasets. For instance, I would like to regress dependent variables on a set of explanatory variables where OLS residuals were spatially autocorrelated. From the regression, I wish to determine the effect of small changes of each explanatory variable on the dependent variable. Any suggestions are appreciated. Thank you, Terry Terry W. Griffin Graduate Research Assistant Agricultural Economics Purdue University 403 W State St West Lafayette, IN 47907 765-494-4257 http://web.ics.purdue.edu/~twgriffi/ <http://web.ics.purdue.edu/~twgriffi/> [[alternative HTML version deleted]]
_______________________________________________ R-sig-Geo mailing list R-sig-Geo at stat.math.ethz.ch https://stat.ethz.ch/mailman/listinfo/r-sig-geo