CSA-34306 Ecological Modelling and Data Analysis in R


Credits 6.00

Teaching methodContact hours
Independent study0
Course coordinator(s)dr. ir. W van der Werf
JC Douma
dr. L Hemerik
Lecturer(s)JC Douma
dr. ir. J van Heerwaarden
dr. L Hemerik
dr. D Rozendaal
dr. ir. W van der Werf
Examiner(s)JC Douma
dr. L Hemerik
dr. ir. W van der Werf

Language of instruction:


Assumed knowledge on:

We assume that students following this course have basic familiarity andhands-on skill with respect to:
- basic ecological models;
- basic calculus and algebra (derivatives, function analysis);
- elementary statistics (probability theory).
Such knowledge is, e.g., taught in the following courses:
PEN-10503 Ecology I and PEN-20503 Ecology II;
MAT-15303 Statistics 1 and MAT-15403 Statistics 2; 
MAT-14803 Mathematics 1 and MAT-14903 Mathematics 2; 
REG-31806 Ecological Methods I or MAT-20306 Advanced Statistics.

Continuation courses:

MSc Thesis.


Note: this course has a maximum number of participants. The deadline for registration is one week earlier than usual. See academic year:(http://www.wur.nl/en/Education-Programmes/Current-Students/Agenda-Calendar-Academic-Year.htm)->Registration for Courses.
Ecological modelling, based on field data, has become an indispensable tool in ecological research to analyse data and propose plausible mechanistic models and mechanistic explanations for observed phenomena. Thiscourse presents a conceptual framework and the hands-on skills for ecological modelling, covering elementary functions and probability distributions needed to mathematically model processes and data, and confront models with the data,using state of the art statistical methods.

Learning outcomes:

After successful completion of this course students are expected to be able to:
- understand major concepts in ecological model fitting and data analysis in R, as presented in Bolker (2008);
- apply major concepts in ecological model fitting and data analysis in R, as presented in Bolker (2008);
- analyse a real-life ecological problem in terms of the key variables characterizing the ecological system;
- evaluate the appropriateness of competing models for the same data, based on underlying mechanistic assumptions and information theoretic criteria;
- create, using R code, a model for an ecological system, fit the model to data, choose the best model using information criteria, and address a real-life ecological question;
- students develop an active learning style, that helps to acquire skills and insight in a broad sense. Those skills include, but are not limited to, articulating questions, engaging in class discussion, and presenting theory to peers.


This course is not the usual course in which teachers present theory and students follow lectures and make assignments. On the contrary, we use a flipped classroom format where students present and discuss theory, and apply the concepts in case studies, according to the students’ design. The teachers give guidance in the learning process by explaining techniques for modelling, data analysis and programming, as needed. This learning format requires a high degree of independence of the students and has been proven to be stimulating and productive. Attitudes that strengthen learning, such as articulating questions, engaging in discussion, interaction and interdependence with fellow students and teachers, as well as independent problem solving, are reinforced.
Students are expected to participate actively in class discussion and each student should give a presentation on the theory. Some (ecological) datasets are analysed during practicals and the results will be discussed in the group. The course is completed with a project in which the students should demonstrate skill and insight in the application of theoretical concepts to an actual scientific problem and dataset. The project outcomes are presented orally, and R codes are shared.
In the beginning of the course, we reserve time for a crash course in R. The objective of the course is, however, not to become an R programmer but to develop the knowledge, insights and skills to use R for advanced mathematical analysis of biological data.


A mark is given on the basis of three components:
- a written test on theory and concepts (25%);
- assessment of the theory presentation (25%); 
- a group paper/design on the application of the concepts andthe elaboration of computer codes in R in a case study (50%).
The required minimum mark for each component for a final passof the course is 5.0.


Ecological Models and Data in R by Ben Bolker, Princeton UniversityPress, 2008. 
Mixed Effects Models and Extensions in Ecology with R byAlain Zuur et al., Springer, 2009.Thesis.

Restricted Optional for: MBIBiologyMScD: Spec. D - Ecology2AF
MPSPlant SciencesMScC: Spec. C - Natural Resource Management2AF
MPSPlant SciencesMScA: Spec. A - Crop Science2AF