Bayesian Population Modelling | PWRC

Currently listed training opportunities (short courses, workshops, meetings...) -- software neutral.

Bayesian Population Modelling | PWRC

Postby cooch » Mon May 17, 2010 4:30 pm

Intermediate-level workshop

"Bayesian population analysis using WinBUGS"

Instructors: Marc Kéry and Michael Schaub, Swiss Ornithological Institute
Date: 1-5 November 2010 (5 full days)
Venue: Patuxent Wildlife Research Center, Laurel, MD, USA
Costs: $600 ($400 grad students); 2 wild-cards are available (*).

The analysis of population distributions, abundance, and demographic parameters (e.g., survival) form the core of ecology and its applications, such as conservation and monitoring science. In recent years, much progress has been made in the development of methods and computer algorithms to fit the statistical models involved in such analyses. In particular, the Bayesian statistical analysis and the revolutionary general-purpose software package WinBUGS have opened up new possibilities for ecologists to conduct fairly complex population analyses.

This course introduces some key models used in the analysis of distribution, abundance and survival, as well as their spatial and temporal patterns, in a Bayesian analysis framework. We use programs R and WinBUGS to fit and understand some of the most widely used models for the analysis of animal and plant populations. These include:

- Poisson generalized linear mixed model (e.g., Link and Sauer 2002) and state-space models (e.g., Dennis et al. 2006) to analyse population dynamics with partial accounting for observation error,
- Site-occupancy models (MacKenzie et al. 2002, 2003) for the analysis of species distributions and binomial mixture models (Royle 2004) for the analysis of distribution and abundance with full accounting for observation error,
- Closed-population models for population size,
- Cormack-Jolly-Seber and ring-recovery models for estimating survival rates, and
- Integrated population models (Besbeas et al. 2002; Schaub et al. 2007)

This is an introductory-level workshop with about equal amount of time spent on lecturing and solving exercises. No previous experience with program WinBUGS, or Bayesian statistics, is assumed. However, a good working knowledge of modern regression methods (ANOVA, ANCOVA, generalised linear models) and some exposure to program R (or another programming language) is required.

Send applications to Andy Royle, andy_royle@usgs.gov by 1 July 2010 at the latest.
cooch
 
Posts: 1628
Joined: Thu May 15, 2003 4:11 pm
Location: Cornell University

Return to Training, Workshops & Meetings

Who is online

Users browsing this forum: Bing [Bot] and 53 guests