3 credits
Fall 2025 Lecture
Examines the assumptions and utility of statistical and other data analytic techniques that are encountered commonly or increasingly being used in ecological research. Emphasis is placed on the potential applications of these quantitative methods in an ecological context. Topics include traditional multivariate methods (cluster analysis, principal components, factor analysis, discriminant analysis, multidimensional scaling, correspondence analysis), generalized linear models (logistic, Poisson, and ordinal regression and derivatives), randomization methods, information-theoretic model selection and inference, and hierarchical models. An introduction to Bayesian analysis is provided for generalized linear (and mixed) models, with applications to (meta) population and (meta) community ecology. Prerequisite: BIOL 58210 or ENTM 64200 or STAT 51200, or consent of instructor. Knowledge of linear algebra and experience with R is desirable but not essential.
Learning Outcomes1Determine the appropriate statistical tool to use when confronted with most questions and data types.
2Be familiar with the assumptions underlying these methods.
3Have some familiarity with software required to apply the methods.
4Offer a basic interpretation of results provided.
Restrictions
made by Purdue students.