![]() |
Science, Technology and Engineering |
![]() |
School of Life SciencesDepartment of Environmental Management & EcologyWorkshop on Analysis of Multivariate Data from Ecology and Environmental Science, using PRIMER v6La Trobe University , Albury-Wodonga Campus, Monday 9th July to Friday 13th July 2012.Presented by:Professor Paul Somerfield (Plymouth Marine Laboratory, UK) Course Content:- This 5- day workshop will cover the statistical analysis of assemblage data (species by samples matrices of abundance, area cover etc) and/or multi-variable environmental data which arise in a wide range of applications in environmental science and ecology, from environmental impact assessments, through fundamental community ecology studies and monitoring of widescale biodiversity change, to biomarker studies and purely physical or chemical analyses - Based on the PRIMER package (Plymouth Routines In Multivariate Ecological Research), a worldwide standard software tool used in over 7000 SCI-listed papers for analysis of aquatic assemblages and, increasingly, terrestrial, paleontological, microbial and genetic data, also for model output, in ecotoxicology, epidemiology, sociology etc. - The workshop covers definitions of similarity, clustering (CLUSTER), ordination by non-metric multi-dimensional scaling (MDS) and principal components analysis (PCA), hypothesis testing on similarity matrices (ANOSIM) and other permutation tests (RELATE), linking biotic patterns to environmental variables (BEST), identifying species responsible for the observed community pattern (SIMPER, BEST), comparison of ordinations (2STAGE, eg 2nd stage MDS), dominance curves and (bio)diversity indices, including measures based on taxonomic relatedness of species (TAXDTEST). All other features of PRIMER v6 are also covered: choice between over 50 (dis)similarity measures, including dispersion-weighted and relatedeness-based coefficients, new 'exploratory' permutation tests for structure in a priori unstructured samples (SIMPROF) and optimal biota-environment relationships (the latter also examined by non-parametric multivariate regression trees, LINKTREE). Also covered are tests for dominance curves (DOMDIS), SIMPER analyses for 2-way layouts and abiotic variables, missing data algorithms for environ-mental data, merging of non-matching species lists etc. - Also briefly demonstrated (though not covered in detail, since they require another 5-day course!) will be the ‘add-on' PERMANOVA+ routines to PRIMER6, which add 'semi-parametric' multivariate analyses, e.g. the extension of permutation tests to complex designs (PERMANOVA), regression (DISTLM) and dispersion tests (PERMDISP). - The workshop will be led by Dr Paul J Somerfield (Plymouth Marine Lab, UK). Paul is a senior researcher in community ecology and quantitative methods at the PML, spearheading the laboratory's biodiversity research. He has been responsible for some of the methodology in the current version of PRIMER and has much experience of using the package creatively in a wide range of applications (marine and terrestrial, microbial and genetic, etc). -‘Hands-on' lab sessions will use real literature case studies, analysed with PRIMER . P articipants are also encouraged to bring some of their own data to the course. The emphasis throughout is on practical application and interpretation, the theoretical aspects (e.g. the multivariate statistical methods which are the core of the course) being carefully selected to be those that are simple to describe and understand. No prior statistical knowledge is assumed. Course prorgamme available in 2012.VenueThe workshop will be held in Computer Lab 1, Main Building , La Trobe University, Albury-Wodonga Campus, University Drive , Wodonga VIC Australia 3690.
Workshop costs
Contact and registration
For further information please contact the local organiser , Rachel Gorman, e-mail: r.gorman@latrobe.edu.au , phone: +61 2 60249885. Content Approved by: Head of Department
|
|