Description
Installation and management of R packages. Review of packages. Input
and output of data.R session.Elements of the language. Plotting
functions and parameters.Basic R programming and automatize
tasks.Preparing statistical reports using R.Analysis of vector and
raster cartography, also connecting with GRASS and QGIS.Experimental
design. Hypothesis contrast, ANOVA. Basic multivariate
statistics.Diversity
and multivariate analysis: ordination and gradient analyses, ENFA
(Ecological Niche Factor Analysis), habitat suitability maps,
metapopulation simulations.Construction, optimization and evaluation of
linear models. Representation and spatial interpretation.Construction,
optimization and evaluation of non-linear models. Representation and
spatial interpretation.
Prerequisites:
This course requires some prior
experience in statistics and elemental mathematics. Knowing
object-oriented programming is not needed.
Course format
This course is divided
into 10 theoretical-practical sessions of 4 hours long, including
assignments through which you can practice your mastery under
supervision.
We will provide students with a selection of data sets
with which to work, however participants are encouraged to bring their
own data.
Students: 250 Euros
Other participants: 350 Euros
Grants: We offer 4 grants for students. The grant will cover the half of the expenses for the course.
If
you are interested, you should send a short CV, a justification of your
situation and a letter of motivation, explaining why and how do you
think this course will improve you and your professional development,
and how the grant will help you. This information must be send to: fcgarcia@ualg.pt
The decision won't be subjected to appeal.
Deadlines
Call for grants: Until 26th February
Resolution of grants: 29th February
Inscriptions: January - April
Start sessions: April
Abstract
Ecological research is becoming increasingly quantitative, yet students often opt out of courses in mathematics and statistics, unwittingly limiting their ability to carry out research in the future. This course provides a practical introduction to quantitative ecology for students and practitioners who have realised that they need this opportunity.
The course is addressed to people who were perhaps more confused than enlightened by their lectures in statistics and who have never used a computer for much more
than word processing and data entry. From this starting point, it slowly but surely instils an understanding of mathematics, statistics and programming,
sufficient for initiating research in ecology. The course's practical value is enhanced by extensive use of biological examples and the computer language R for
graphics, programming and data analysis.
R is a language and environment for statistical computing and graphics (http://www.r-project.org). R provides a wide variety of statistical (linear and non-linear modelling, classical statistical tests, time-series analysis, classification, clustering, ...) and graphical techniques. Many users think of R as a statistics system. Furthermore, it is an environment within which statistical techniques are implemented. R can be extended (easily) via packages, covering a very wide range of modern statistics and much more. It has become the \textit{lingua franca} among statisticians, and is increasingly being used for data analysis among researchers. Many advanced or recent statistical and graphical/visualisation techniques are only available in R.
This course is also intended for anyone who wishes to learn how to use the powerful open source statistical software package R. The course requires no previous knowledge of R. However, some prior experience in statistics and elemental mathematics is required.
Expected learning outcomes
The focus will be on giving the participants practical experience with the software. The course material will be a blend of introductory lectures on R and practical sessions.
This course does not intend to be a full introduction to statistics. The objective is to review the state-of-the-art statistical methods for analysis of ecological data, demonstrating the power of open source statistical software. We will provide hands-on experience for standard data analysis (cookbook), enabling participants to use the software on their own problems (take-home software).
Participants will be introduced to the R environment and how to manage their R working space and data.
Participants will learn how to write, comment and save scripts, how to prepare the results in a variety of formats that can easily be embedded in papers and presentations and how to prepare statistical reports into R. Participants will learn how to create standard statistical graphs such as bar plots, histograms, box-plots, scatter-plots and time series plots. They will also learn how to enhance these
plots through the addition of titles, labels, legends, text annotations, colours and symbols.
Next, participants will learn how to create multi-panel and 3D plots.
Finally, we will walk through quantitative ecology concepts and methodologies, including sampling design, data preparation, diversity analyses, basic ANOVA methods, hypothesis testing, multivariate analysis, linear and non-linear modelling.
Sessions
aRound Description: installation and management of R packages. Review of packages. Input and output of data.
useR Description: R session. Elements of the language.
gRaphics Description: plotting functions and parameters.
autoR Description: basic R programming and automatize tasks.
wRite Description: preparing statistical reports using R.
Rspatial Description: analysis of vector and raster cartography, also connecting with GRASS and QGIS.
aRtistics Description: experimental design. Hypothesis contrast, ANOVA. Basic multivariate statistics.
multivaR Description: diversity and multivariate analysis: ordination and gradient analyses, ENFA (Ecological Niche Factor Analysis), habitat suitability maps, metapopulation simulations.
lineaR Description: construction, optimization and evaluation of linear models. Representation and spatial interpretation.
modelaRt Description: construction, optimization and evaluation of non-linear models. Representation and spatial interpretation.
About the Instructor
Fernando Cánovas is a postdoctoral fellowship who belongs to the Marine Resources Management Team (http://www.maresma.org, under the umbrella group BEE - Biogeography, Ecology and Evolution) at the Centre of Marine Sciences (CCMAR). He is interested in solving questions about biology and evolution of species and populations by integrating genetic and quantitative ecology tools. He leads the Open Marine Technology and Engenering laboratory (OpenMarTech), which is part of MaResMa team since 2015. OpenMarTech is dedicated to research about use and adaptation of open source technologies in marine research at both software and hardware levels. The relevance of developing research in this field results from the fact that those technologies have been dramatically expand the possibilities to develop new tools and concepts. With a multidisciplinary team, OpenMarTech is organized around the development of research tools (both hardware and software), and activities (both fundamental and applied levels), complemented by the promotion of dissemination actions.
11.01.2015