Date of Completion

8-29-2019

Embargo Period

8-28-2020

Keywords

spatial capture recapture statistics population size abundance rjmcmc

Major Advisor

Dr. Haim Bar

Associate Advisor

Dr. Kun Chen

Associate Advisor

Dr. Ming-Hui Chen

Associate Advisor

Dr. Dipak Dey

Field of Study

Statistics

Degree

Doctor of Philosophy

Open Access

Open Access

Abstract

Over the past two decades there have been many advancements in modeling capture-recapture (CR) data to account for emerging data collection technology and techniques. Spatial capture-recapture (SCR) models have been introduced to estimate population size and numerous other demographic parameters from spatially explicit CR data. Here we offer a comprehensive review of the development of CR modeling up to and including SCR models.

We then introduce a new SCR model which allows for attractions between individuals via their daily movements. A simulation study is used to demonstrate accounting for these attractions can improve population size estimation. Additionally, we apply our model to an iconic SCR dataset to estimate the population size and attraction parameters of a Bengal tiger (\textit{Panthera tigris tigris}) population.

To conclude we present a reversible-jump Markov chain Monte Carlo (RJMCMC) approach for parameter estimation which has not previously been extended to SCR models. Simulation studies are presented to show the superior computational efficiency of this proposed approach. We also demonstrate the application of this RJMCMC method to SCR data by estimating the size of an American black bear (Ursus americanus) population.

Share

COinS