Title :USE OF STATISTICAL ANALYSIS IN BIOLOGICAL SCIENCES: DO BIOLOGISTS NEED BETTER TRAINING, BETTER DATA OR SIMPLY BETTER QUESTIONS?
Speaker: Associate Professor Gerry Quinn
School of Biological Sciences
Time: 4:00p.m. Wednesday 13th October 2004
Venue: Red Centre Building Room RC-3084
near Barker Street Gate 14
his seminar will explore the use of statistical analyses in the biological sciences from the perspective of a practicing, quantitative ecologist. Statistics has played an important role in ecology, at least partly due to the complexity of ecosystems and high levels of natural variability.
However, the majority of ecologists still use a small set of very traditional analyses and often constrain their designs and their models (even their ideas) to fit these standard methods.
Some of the issues to be considered in this
seminar include ecologsists' fascination with null hypothesis testing and statistical
significance, the increasing use of Bayesian methods, the design of experiments and sampling programs, and the use/abuse of linear models, especially model selection and modeling correlated observations. Finally, the issue of statistical training for +biologists will be discussed.