1

I am new to spatial statistics.

I am trying to determine if points close together are more or less similar. Specifically, I have a series of lat/long points for alligators nests. At some nests, one male contributed to the nest and at other nests more than one male contributed to the nest. I am to see if singly sired nests are more likely to be found near other singly sired nests or if multiply sired nests are more likely to be found near multiply sired nests. I do not need a detailed step by step guide to solve this problem. I just need someone to point me in the direction of where I should start with R.

PolyGeo
  • 65,136
  • 29
  • 109
  • 338
user123188
  • 11
  • 1
  • Welcome to GIS SE! As a new user be sure to take the [Tour] to learn about our focussed Q&A format. If you need to ask a similar question for other software products then feel free to in separate questions. – PolyGeo Jun 29 '18 at 01:09
  • Take a look at this post: https://gis.stackexchange.com/questions/42427/determining-if-trees-within-forest-gaps-are-clustered-using-r/42485#42485 – Jeffrey Evans Jun 29 '18 at 01:40
  • You are describing Point Pattern Analysis (PPA) which is a fairly well developed field. However, one thing to keep before implementing any of the recommended analysis is that one assumption of these statistics is that they are a population and do not represent a sample. This is because you are testing against an expected null (Complete Spatial Random or CSR) and a sample will not adequately represent a spatial process when tested against the null. – Jeffrey Evans Jun 29 '18 at 21:34

1 Answers1

1

R might be the most straightforward tool for this job.

I would suggest looking into the K-, L- and G-Function tools in the "spatstat" package. They will help you see if any patterns in your data suggest spatial clustering. I think that by subsetting your data into two groups (single male vs. multiple male) you can get the answer you're looking for.

This is a link to the documentation PDF. Spatstat is an extensive package, but the syntax for what you're trying to do is pretty straightforward.

Josh Beauchamp
  • 116
  • 5