Dear colleagues,
I have a dataset consisting of continuous, categorical, and binomial (presence/absence) variables, and I need to test for spatial autocorrelation in each one of them. I have done it already for the continuous variables using the standard Moran's I (Moran.I function of the ape R-package), but I understand I cannot do this for my other variables. What other R alternatives do I have to test for spatial autocorrelation in categorical and binomial (presence/absence) variables?
Thanks in advance!
Spatial Statistics Toolbox in ArcToolbox ( Arc GIS) provides couple of tools to measure spatial autocorrelation and analyze spatial patterns (clustering or dispersion) and assess feature spatial distributions.
These include
Spatial Autocorrelation (Global Moran's I),
High/Low Clustering (Getis-Ord General G),
Cluster and Outlier Analysis (Anselin Local Moran's I),
Hot Spot Analysis (Getis-Ord Gi*), and
Directional Distribution (Standard Deviational Ellipse).
Hope this helps .....
I'm not sure what autocorrelation means in a categorical variable. Can you explain?
Hey Rodolfo,
you may also want to check out these two papers:
http://link.springer.com/article/10.1007%2Fs10109-009-0100-1
http://www.tandfonline.com/doi/abs/10.1080/13658816.2011.620571#.Vsju1OZ5VaU
Best wishes,
René
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Statistical Software
- R Statistical Package