[R] 3D spatial statistics

Greg Jefferis jefferis at stanford.edu
Thu Dec 6 09:52:34 CET 2001

Dear R Users,

This is only partly an R question, but I would be very grateful if anyone
could offer some suggestions for approaches or packages I could use in R.  I
have 11 sets of points in 3D (synapses in a region of a fly's brain for 11
different kinds of neurons as it happens); each set has between 80-250
points distributed in an irregularly shaped cloud.  I would like to

a) a measure of similarity of the distributions of points between pairwise
combinations of the 11 groups; i.e. using colour to represent the 11 groups,
how similar are the distributions of 'red' and 'green' points - is this more
or less than red and blue points.

b) using some kind of thresholding to remove outliers, a volume occupied by
these points; a convex hull would be not be appropriate as some of these
clouds look like a 3D boomerang.

I am aware that there are some spatial stats packages which might be useful
in 2D situations.  Are there any functions which might be applicable for
these three dimensional cases.  If anyone could suggest an appropriate
textbook for a non-specialist in this general area of statistics that would
also be much appreciated.  Very many thanks,

Greg Jefferis.

Incidentally I have approached (a) rather crudely by making use of the knn
function in package = class for each pairwise combination of the 11 groups.
Briefly for every single point I figure out the proportion of its k nearest
neighbours that are of the same 'colour' and divide that by the proportion
of all points that are of that 'colour'.  I then average over all the points
presently under consideration, to get an index of how homogeneously
distributed the two sets of points are with respect to each other.

Greg Jefferis,                          Lab Address: Liqun Luo, Herrin 144
Neurosciences PhD Programme &                e-mail: jefferis at stanford.edu
Dept Biological Sciences,                       Lab: (650) 725 5809
Gilbert Biology Building,                       Fax: (650) 723 0589
371 Serra Mall,
Stanford, CA 94305-5020.                       Home: (650) 497 1135

r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch

More information about the R-help mailing list