Analysis of Environmental Data

Helsinki: Provisional timetable Jan 14 - 18th, 2008
 

		Lecture	Practical
Mon	am	Introduction - aims of the course, approaches to statistical modelling, overview of methods, terminology.	Introduction to R – installing R, data types, functions, graphics, data import and export.
	pm	Exploratory data analysis and graphics – summarising data, data transformation, outliers, visualising uni-, bi- and multivariate relationships.	EDA - Using R to summarise, display and graphically explore environmental data.
Tues	am	Introduction to regression – bivariate least squares regression, significance test, assumptions, model diagnosis, prediction.	Linear regression in R - building and diagnosing linear regression models in R.
	pm	Multiple regression and analysis of variance – variable selection and model building, one-way and two-way ANOVA, mixed predictors.	Multiple regression and ANOVA in R – significance testing, manual and automated model building, diagnostics, multiple comparisons.
Wed	am	Introduction to ordination - principal components analysis.	Principal components analysis in R  – model fitting and graphical display.
	pm	Correspondence analysis and related methods – CA, DCA, metric and non-metric multidimensional scaling, comparing ordinations.	CA, DCA, MDS and nMDS in R – model fitting and interpretation, comparing ordinations.
Thur	am	Constrained ordination – Canonical correspondence analysis, redundancy analysis, partial ordination, variance partitioning, permutation tests.	Constrained ordination in R – variable selection, significance testing, ordination diagrams, variance partitioning.
	pm	Classification and analysis of grouped data –overview of methods, dissimilarity coefficients, hierarchical methods, TWINSPAN, k-means, validation, comparing classifications.	Classification in R – calculating dissimilarities, clustering methods, display of results, significance of groups, identification of indicators, Classification and regression trees, graphical tools..
Fri	am	Transfer functions – overview of methods, weighted averaging, WAPLS, MAT, diagnostics & evaluation.	Transfer functions with C2 – model fitting, diagnosis, evaluation of reconstruction.
	pm	Advanced regression topics - Generalised linear models, generalised additive models, weighted averaging, quantile regression.	Advanced regression in R - Species response modelling with GLMs, GAMs, and WA.