State-space models: the good, the bad and the ugly
Dr. Marie Auger-Méthé
Institute for the Oceans and Fisheries, and UBC Dept. of Statistics
Friday, January 12, 2018
AERL Theatre (120)
State-space models (SSMs) are increasingly used in ecology to model time-series such as animal movement paths and population dynamics. This type of hierarchical model is structured to account for two levels of variability: biological stochasticity and measurement error. Because they can account for large measurement error, they are particularly popular to study marine animals for which it is often hard to get accurate time-series of geographic locations and population counts. SSMs are flexible. They can model linear and nonlinear processes using a variety of statistical distributions.
In this talk, Dr. Auger-Méthé will use marine movement data to introduce SSMs and to demonstrate when these models are useful and when they can fail. She will also highlight new tools that can help fit state-space models to data.
Marie Auger-Méthéis an assistant professor in the Institute for the Oceans and Fisheries and in UBC’s Department of Statistics. Most of her work is interdisciplinary in nature and at the intersection between ecology, statistics, and marine sciences. Her recent focus has been on developing and applying statistical models to understand the movement and space use of marine species. Prior to starting at UBC, Marie did her PhD at the University of Alberta, and a BSC, MSc, and Postdoctoral fellowship at Dalhousie University.
Next week: Fiorenza Micheli
David and Lucile Packard Professor of Marine Science and Co-Director, Center for Ocean Solutions
Hopkins Marine Station
IOF Seminar Schedule: http://oceans.ubc.ca/education/seminars-lecture-series/fish-500-lecture-schedule/
Photo credit: Victor from flickr/ Creative Commons