Dynamic models in R

You are here

Logo_perc_sense.jpg

Dynamic Models in R:

Programming, parameter estimation and model selection

To be announced

Scope

Ecological modelling, based on field data, has become an indispensable tool in ecological research. It consists of a number of steps: analysing data, proposing plausible mechanistic models and mechanistic explanations for observed phenomena, and selecting models based on maximum likelihood or an information criterion. This course presents a conceptual framework for ecological modelling: covering elementary growth models and probability distributions needed to mathematically model processes. The models are confronted with the data, using state of the art statistical methods. The course presents techniques for dynamic simulation, model fitting, parameter estimation, and model selection based on maximum likelihood and information theory. While the theory has emerged from the field of ecology, it has shown to be widely applicable in the life sciences. The course is taught with R as the programming language because it is freeware and it allows flexibility in handling and modelling data.

Teaching method

The conceptual framework is taught from the book “Ecological Models and Data in R” by Ben Bolker, Princeton University Press, 2008. Examples are drawn from the field of (agro-)ecology. The course consists of theory lectures, hands-on practical sessions and a case study to synthesize the acquired skills and knowledge. The case study is presented and discussed on the last day of the course.

Learning outcomes

After completing the course, the participant

  1. is able to program a discrete time dynamic model in R
  2. is able to program a continuous time dynamic model in R
  3. is able to add stochastic variation to a dynamic model in R
  4. is able to choose appropriate probability models to represent biological variation
  5. understands the concept of maximum likelihood
  6. is able to program a maximum likelihood estimation for a single parameter in R
  7. understands conceptually the difference between process error and observation error
  8. understands the principles of different methods of parameter estimation of ecological models
  9. is able to program a parameter search algorithm for ecological model calibration in R
  10. understand and apply the principles of model selection to select the best model
  11. is able to fit and select an ecological model to an actual problem in R
 
Programme
 

Day 1: Dynamic simulation in R

Day 2: Stochastic simulation

  • Making dynamic loops in R
  • Simple population models (discrete and continuous time)
  • Simple growth models

Day 3: Fitting an ecological model with maximum likelihood

  • Statistical distributions for stochastic processes
  • Stochastic simulations

Day 4: Parameter optimization and model selection

  • Uncertainty/Confidence limits
  • Model selection

Day 5: Case studies

Day 6: Case study presentations

General information
 
Target Group The course is aimed at PhD candidates and other academics.
Group Size Min. 20, max. 30 participants
Course duration 6 days
Language of instruction English
Frequency of recurrence Once a year, or once every two years
Number of credits 1.8 ECTS
Lecturers Dr.ir. Bob Douma (Centre for Crops System Analysis, Wageningen University & Research), Dr. Lia Hemerik (Biometris, Wageningen University & Research) and Dr.ir. Wopke van der Werf (Centre for Crops Systems Analysis, Wageningen University & Research)
Prior knowledge Basic knowledge of R (e.g. installing packages, reading data-files, linear regression), and basic knowledge on statistics (e.g. linear regression, anova).
Location Wageningen University Campus
Options for accommodation Accommodation is not included in the fee of the course, but there are several possibilities in Wageningen. For information on B&B's and hotels in Wageningen please visit proefwageningen.nl. Another option is Short Stay Wageningen. Furthermore Airbnb offers several rooms in the area. Note that besides the restaurants in Wageningen, there are also options to have dinner at Wageningen Campus.
More information

Claudius van de Vijver (PE&RC)
Phone: +31 (0) 317 485116
Email: claudius.vandevijver@wur.nl

Lennart Suselbeek (PE&RC)
Phone: +31 (0) 317 485426
Email: lennart.suselbeek@wur.nl

Registration of interest

At this moment, this course is not scheduled yet. However, if you register your interest in this activity below, we will inform you as soon as the course is scheduled and registration of participation is opened.