701-1419-00L  Analysis of Ecological Data

SemesterHerbstsemester 2017
DozierendeS. Güsewell
Periodizitätjährlich wiederkehrende Veranstaltung
LehrspracheEnglisch


KurzbeschreibungThis class provides students with an overview of techniques for data analysis used in modern ecological research, as well as practical experience in running these analyses with R and interpreting the results. Topics include linear models, generalized linear models, mixed models, model selection and randomization methods.
LernzielStudents will be able to:
- describe the aims and principles of important techniques for the analysis of ecological data
- choose appropriate techniques for given problems and types of data
- evaluate assumptions and limitations
- implement the analyses in R
- represent the relevant results in graphs, tables and text
- interpret and evaluate the results in ecological terms
Inhalt- Linear models for experimental and observational studies
- Model selection
- Introduction to likelihood inference and Bayesian statistics
- Analysis of counts and proportions (generalised linear models)
- Models for non-linear relationships
- Grouping and correlation structures (mixed models)
- Randomisation methods
SkriptLecture notes and additional reading will be available electronically a few days before the course
LiteraturSuggested books for additional reading (available electronically)
Zuur A, Ieno EN & Smith GM (2007) Analysing ecological data. Springer, Berlin.
Zuur A, Ieno EN, Walker NJ, Saveliev AA & Smith GM (2009) Mixed effects models and extensions in ecology with R. Springer, New York.
Faraway JJ (2006) Extending the Linear Model with R: Generalized Linear, Mixed Effects and Nonparametric Regression Models. Taylor & Francis.
Voraussetzungen / BesonderesTime schedule
The course takes place on Mondays 12:45-15:00 from 25 September until 27 November, with the final exam on Monday 4 December. The last two weeks of the semester are free.

Prerequisites
- Basic statistical training (e.g. Mathematik IV in D-USYS): Data distributions, descriptive statistics, hypothesis testing, linear regression, analysis of variance
- Basic experience in data handling and data analysis in R

Individual preparation
Students without the required knowledge are asked to contact the lecturer before the first lecture date for support with individual preparation.