Has anybody used Stata for tests of spatio-temporal clustering (Mantel,
Knox, k-Nearest Neighbor, ...)?
These tests use data on events that have a spatial (XY coordinates) and
temporal (e.g. date) element, and use all possible (unordered) pairs of
observation (i.e. (N*(N-1))/2) in the data for calculating the products of
time-distances and spatial distance.
I gues it is tedious though not extremely difficult to program. Any help or
guidance is appreciated. For example, how do I generate all unordered pairs
of observations (--cross-- the dataset with itself and then dropping half of
the cases?)
Thanks!
Wim Bernasco
> Netherlands Institute for the Study of
> Crime and Law Enforcement (NSCR)
>
> Postal address
> P.O. Box 792
> NL-2300 AT Leiden
>
> Visiting address
> Wassenaarseweg 72
> 2333 AL Leiden
> The Netherlands
>
> Contact information
>
> Phone +31-71-5278504 (direct)
> +31-71-5278527 (NSCR)
> Fax +31-71 5278537
> Email [email protected]
> Website www.nscr.nl
>
>
>
>
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/