Universität Wien

300325 UE Multivariate statistical methods in ecology (2015W)

3.00 ECTS (2.00 SWS), SPL 30 - Biologie
Continuous assessment of course work

Vorbesprechung/First meeting: 06.10.2015, 15:00, ***SEMINARRAUM LIMNOLOGIE***

Dates: Blocked course February 08.-12. February 2016, Seminarraum Geochemie

2C193 1.OG UZA II, 14:00-18:00. Course language is English. Note combination with

VO (same name, delivered by Gabriel Singer).
Moodle

Registration/Deregistration

Note: The time of your registration within the registration period has no effect on the allocation of places (no first come, first served).

Details

max. 30 participants
Language: German, English

Lecturers

Classes

Currently no class schedule is known.

Information

Aims, contents and method of the course

Statistical data analysis in ecology: descriptive statistics, univariate statistical tests (ttests,
U-test, analysis of variance), bivariate data analysis (correlation, linear and nonlinear
regression), selected regression models (multiple linear regression, ANCOVA,
GLM, GAM), commonly used classic unconstrained and constrained ordination
methods: principal component analysis (PCA), canonical correspondence analysis
(CCA), redundancy analysis (RDA), distance/dissimilarity-based unconstrained and
constrained ordination methods: metric and non-metric multi-dimensional scaling
(MDS, NMDS), canonical analysis of principal coordinates (CAP), multivariate
hypothesis tests (PERMANOVA, permutation tests based on ordinations).

Assessment and permitted materials

80% presence throughout the course, participation in the team work and final
presentation are mandatory. Practical course mark is based on presence and
commitment during the course (UE 50 %), and (team-) presentations about
independently analysed dataset (UE 50 %).

Minimum requirements and assessment criteria

Successful participants will learn to apply the most commonly used statistical
methods in ecology on provided datasets. They will understand how to produce and
interpret graphical and tabular output from univariate, bivariate and multivariate
analyses of ecological datasets as presented in scientific papers and reports. They will
learn how to use the statistical software package R.

Examination topics

The course is scheduled as one block in February 2015 (Feb-8 to Feb-12, afternoons)
and should be attended in combination with the lecture (VO) with the same title and
taking place in the same period in the mornings. The block course is followed by
independent home-based team work. Teams of 2 students each will work on specific
ecological datasets, which will be graphically and statistically analyzed under
guidance. The course then finishes with student presentations to be given during a 1-
day seminar end of February/beginning of March 2016 (exact date will be agreed
upon during the first meeting October 7 2014). The practical course will be based on
the statistical software package R, no previous experience in R is needed.

Reading list

Course Handout with R-relevant information will be provided in the lecture, R-scripts
and datasets will be provided for the practical course.

Dalgaard, P. 2008. Introductory Statistics with R (Series: Statistics and Computing).
Springer Verlag, New York, 364 pp.
Borcard D., Gillet F. & Legendre P. 2011. Numerical Ecology with R. Springer, New
York, U.S.A., 306 pp.

Association in the course directory

MEC-5

Last modified: Mo 07.09.2020 15:43