Skip to content

Assessing residual spatial autocorrelation in a Poisson or Negative Binomial model

5 messages · Karen Lamb, Luis Iván Ortiz Valencia, Roger Bivand +2 more

Original
Karen Lamb
# 
Hi,

I am currently trying to determine a way of assessing whether or not 
there is spatial autocorrelation present in my model residuals and was 
hoping someone could help me with this.

I have information on counts in over six thousand areas, with around 
half of the areas found to have  a count of zero. I decided to fit a 
Zero-Inflated Poisson model and a Negative Binomial as the data is 
greatly overdispersed. However, neither of these approaches take into 
account the likelihood that there is spatial autocorrelation present in 
the data set.

I have been searching for the last two weeks to find appropriate methods 
to fit a spatial glm model. However, as I am new to spatial statistical 
methodology I am finding it difficult to decide how best to do this. It 
am not sure that any of the existing R functions are particularly 
suitable to my use. I am not interested in prediction as I have data on 
a population. I am interested in assessing the coefficients of variables 
and whether or not the variables are significant in determining outcome. 
I have noticed that a lot of analyses use a Bayesian approach which may 
be the way forward.

My question, however, relates to the glm models I have fitted. I have 
included variables which may explain some of the spatial correlations 
such as urban/rural classification. I would like to see if any residual 
spatial autocorrelation remains in the model but cannot find a way of 
doing this. On searching the R-sig-Geo archives the Morans Test or 
Morans I are mentioned. However, I noticed someone had queried using the 
moran test in R for residuals from a logistic regression and had been 
told that lm.morantest() is available for linear regression but there is 
not an alternative for the glm. Has anyone got any suggestions for how 
to check my residuals? Are there particular plots that can be assessed?

Thanks for your assistance.

Cheers,
Karen
Roger Bivand
#
On Thu, 26 Nov 2009, Luis Iv?n Ortiz Valencia wrote:

            

      
      
      
    

        
Rather:

http://cran.r-project.org/view=Spatial

please, the sourceforge site is more for development, and is linked from 
the task view on your nearest CRAN mirror.

While lm.morantest() can be used on glm output objects, no work has been 
done to establish whether this is a sensible idea. It remains problematic 
to simulate spatially dependent discrete variables. However, it is 
possible that if you ignore the "test" of doubtful substance, you could 
track how Moran's I moves when adding variables in an exploratory way. Try 
with a smaller dataset first.

Hope this helps,

Roger

            

      
      
      
    

        

      
      
    

            

      
      
      
    

        

  
    

      
      
    

  


  


      

    

    

      
      

        


  

        

      Marcelino de la Cruz
    

    

      
      #
    

  


  

      
Hi,

You may find useful this:

Dormann et al. 2007. Methods to account for 
spatial autocorrelation in the analysis
of species distributional data: a review. Ecography 30: 609-628,

And the suplementary material with several examples worked in R.

HTH,

Marcelino

        
At 11:46 26/11/2009, Karen Lamb wrote:

            

      
      
      
    

        

      
      
    

        
________________________________

Marcelino de la Cruz Rot

Departamento de  Biolog?a Vegetal
E.U.T.I. Agr?cola
Universidad Polit?cnica de Madrid
28040-Madrid
Tel.: 91 336 54 35
Fax: 91 336 56 56
marcelino.delacruz at upm.es
_________________________________

  
  


  


      

    

    
4 days later