Courses

1) Manipulating big data in R for vegetation scientists

18–19 July 2015, University Campus Bohunice, Masaryk University, Brno
Course leader: Viktoria Wagner, Masaryk University

Vegetation scientists are increasingly challenged to analyse big datasets, which are characterized by their large volume (> 100 MB RAM) and heterogeneity. R is a programming language that offers a wide range of tools to overcome these obstacles. In this course, you can learn how to use R in order to handle and manipulate large datasets. In particular, you will learn how to 1) import large datasets efficiently, 2) perform automatic error checking, 3) spot duplicate observations, 4) manipulate (e.g. melt, cast, subset) your matrix, 5) merge large datasets fast and flexibly, and 5) summarise your data. The core of the course will be packages stringr, taxonstand, data.table and plyr/dplyr. Hands-on exercises will be accompanied by short lectures/demonstrations.

Please bring your notebooks (R runs on Windows, Mac or Linux). Computers might be provided if necessary (please contact the course instructor). Please keep in mind that the ultimate increase in data processing speed will depend on your notebook performance. Installation instructions and course material will be sent to you prior to the course. Datasets and an internet connection (wifi) will be provided. Prior knowledge of R (or any other programming language) is desired but not a must.

The course is limited to 15 participants. This course is one of two independent R-courses offered at the IAVS Symposium. The Symposium participants can register for either one of them or both. This course focuses solely on data manipulation, but not on data analysis.

price € 50

2) Multivariate Analysis of Vegetation Data in R: current practice

25–26 July 2015, University Campus Bohunice, Masaryk University, Brno
Course leaders: David Zelený & Ching-Feng Li (Woody), Masaryk University

This two-day R course will focus on multivariate analysis of vegetation data, mostly ordination and classification. The aim is to demonstrate what we think is good practice in using multivariate methods to analyse vegetation data, mainly how to decide which method is suitable for the given question and data in hand, how to conduct analysis in R and how to interpret and report the results. The class will be a combination of a theoretical overview with practical exercises, based on solving tasks with real vegetation datasets that we will provide. The intended audience are graduate students and researchers whose major is community ecology, with a basic knowledge of statistics and the ability to write basic R scripts.

Computers with Internet and installed R will be provided. You may use your own laptop with preinstalled R program and the administrator right to install new R libraries during the course. Because all the study materials and datasets for practice will be available online, access to Wi-Fi is necessary if you want to use your own laptop.

The course is limited to 30 participants. It is one of two independent R-courses offered at the IAVS Symposium. The Symposium participants can register for either one of them or both. This course focuses on multivariate data analysis and basic methods on data manipulation, but not on special procedures for manipulation of large data sets. If you already know how to calculate variance partitioning using RDA on Hellinger transformed data in R, or if your goal is to learn innovative, fancy and advanced methods, attending this course may be a waste of your time. The methods we will be teaching and practicing on this course are well established and commonly used in vegetation ecology.

price € 50

3) Vegetation Data Analysis Using the JUICE Program

25–26 July 2015, University Campus Bohunice, Masaryk University, Brno
Course leaders: Lubomír Tichý & Flavia Landucci, Masaryk University

This two-day course will cover the main methods of classification and analysis of vegetation data using JUICE and related programs. The course will provide an introduction to data structures and types, a solution to nomenclature issues, data stratification, fidelity, classification algorithms, parameterisation of vegetation types, and linking vegetation-plot data with plant traits. Participants are expected to bring and use their own laptops. The course is limited to 30 participants.

price € 50