I would like to know (in a practical manner) how to calculate the bivariate (or cross) space-time K-function for clustering analysis between different types of events?
Does anyone have a sample script, or any other document that describes the implementation of the method in R?
Lynch and Moorcroft (2008) describe the implementation of the method using the splancs package:
"Note that this function (space–time cross-K-function) may be estimated using a weighted average of the more traditional bivariate K-function Kbf(s) (as estimated by the k12hat function in the R package ‘‘splancs’’ (R Development Core Team 2005)), where the insect point process and the fire point process are drawn from different years with a given lag time".
Some papers that used this method:
Lynch and Moorcroft (2008) - http://www.nrcresearchpress.com/doi/abs/10.1139/X08-143#.WKFTfVUrJhE
Flaxman et al. (2013) - http://repository.cmu.edu/cgi/viewcontent.cgi?article=1402&context=heinzworks
Wooditch and Weisburd (2015) - http://link.springer.com/article/10.1007/s10940-015-9259-4
Thanks in advance!
Hello Sacha,
I do not know if you found a solution, but I have the same question right now and so far I found this blog (http://blog.jlevente.com/understanding-the-cross-k-function/ ) and this tutorial (https://github.com/jlevente/publications/tree/master/cross-k). For me these explanations are useful, although I am struggling to apply on my data.
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Statistical Software
- R Statistical Package