Go to  Advanced Search

Statistical methods for assessing habitat preferences

Show full item record

Files in this item

Files Size Format Description   View
ubc_2000-0002.pdf 2.226Mb Adobe Portable Document Format   View/Open
 
Title: Statistical methods for assessing habitat preferences
Author: Ayers, Dieter
Degree Master of Science - MSc
Program Statistics
Copyright Date: 2000
Abstract: It is often the case that samples are taken in a non-random fashion. This thesis attempts to define a methodology by which some analysis can be performed on a specific kind of non-random sample. In studies of wildlife behaviour, a common method of sampling involves tagging an animal and relocating it in subsequent time periods. Considering the number or type of animal present at sampling locations as a random sample is erroneous, as the locations were chosen by the animal and not in a random fashion. Further, with data such as this is not possible to draw conclusions about areas where no animals were observed, as it is unknown whether these areas were truly free of animals. We treat the observed data as conditional on the presence of an animal, and then use a Bayesian approach to estimate the probability of finding animals in any given location. This results in a method that allows for mapping the propensity of a certain area to be chosen by an animal in the future.
URI: http://hdl.handle.net/2429/10184
Series/Report no. UBC Retrospective Theses Digitization Project [http://www.library.ubc.ca/archives/retro_theses/]

This item appears in the following Collection(s)

Show full item record

All items in cIRcle are protected by copyright, with all rights reserved.

UBC Library
1961 East Mall
Vancouver, B.C.
Canada V6T 1Z1
Tel: 604-822-6375
Fax: 604-822-3893