Re: [R] Model design

2011-12-16 Thread ONKELINX, Thierry
ELINX, Thierry CC: r-help@r-project.org Onderwerp: Re: [R] Model design Hi Thierry I looked at running an ANOVA but I have spatial autocorrelation in the data set as indicated by Variograms and significant moran's I i.e the cells closer together are more likely to be similar than expected unde

Re: [R] Model design

2011-12-16 Thread alfreda morinez
Hi Thierry I looked at running an ANOVA but I have spatial autocorrelation in the data set as indicated by Variograms and significant moran's I i.e the cells closer together are more likely to be similar than expected under a normal distibution - is it possible to make this approach take it into c

Re: [R] Model design

2011-12-16 Thread ONKELINX, Thierry
Dear Alfreda, anova(area_grass) will tell you IF the average grass area is different among areas. If you want to know WHICH areas are different from each other, then you have to do some multiple comparisons. You can use the multcomp package: e.g. library(multcomp) glht(area_grass, linfct = mc