12. November, 9:30 bis 19. November 2018, 17:30 Uhr
IGB, Müggelseedamm 310, lecture hall
Die Anmeldefrist für die Veranstaltung ist leider abgelaufen.
This course is suitable for anyone with a solid understanding of basic statistics and well-practiced use of R
Lecturer: Matthew Talluto
* Knowledge of basic statistics (probability distributions, linear models)
* R programming skills
This course will cover the basics of Bayesian statistical methods with applications in ecology. Bayesian methods are a powerful set of tools that are increasingly used with complex ecological data. These methods can also be extended quite easily byond simple statistics to include process-based/mechanistic models. This course is suitable for anyone wanting to improve their quantitative skills and learn how to design custom analyses.
* Review of probability theory, relationship between probability and statistical analysis
* Review of maximum likelihood
* Bayes' Theorem and its applications
* Markov-chain Monte Carlo (MCMC) and other parameter estimation methods
* Model selection, evaluation, visualisation
* Hierarchial models
* Other topics depending on demand
Participants are expected to attend the entire course. We will perform all analyses in R. Expert-level R-knowledge is not required, but you should be comfortable with the basics (reading data in, data frames, basic plotting, creating and using variables). For more complex models, we will specify them with the free modelling language Stan. Instructions for downloading and installing all necessary software will be provided before the course. At minimum, you will need a laptop computer with R or Rstudio installed. Participants are also strongly encouraged to bring a dataset they are willing to share with a statistical question they would like to ask. Working in small groups to design, analyse, and present the results of this analysis will be a major portion of the course. If you don't have data, you can still attend, we will find a group for you to work with and find a dataset, if necessary.