“Spatial analysis of ecological data using R”
Delivered by Prof. Jason Matthiopoulos
http://prstatistics.com/
This course will run from 11th – 17th April 2016 at Millport Field Station, Isle of Cumbrae, Scotland
The course will cover the concepts and R tools that can be used to analyse spatial data in ecology covering elementary and advanced spatial analysis techniques applicable to both plants and animals. We will investigate analyses appropriate to transect (e.g. line surveys, trapping arrays), grid (e.g. occupancy surveys) and point data (e.g. telemetry). The focal questions will be on deriving species distributions, determining their environmental drivers and quantifying different types of associated uncertainty. Novel methodology for generating predictions will be introduced. We will also address the challenges of applying the results of these methods to wildlife conservation and resource management and communicate the findings to non-experts.
Course content is as follows
Day 1: Elementary concepts
Module 1 Introductory lectures and practical; this will cover the key questions in spatial ecology, the main types of data on species distributions, concepts and challenges and different types of environmental data, concepts and challenges; useful concepts from statistics; Generalised Linear Models
Module 2 GIS tools in R: Types and structure of spatial objects in R, generating and manipulating spatial objects,
projections and transformations, cropping and masking spatial objects, extracting covariate data and other simple
GIS operations in R, optionally plotting simple maps
Day 2: Overview of basic analyses
Module 3 Density estimation, Spatial autocorrelation, Smoothing, Kernel Smoothers, Kriging, Trend-fitting (linear, generalised linear, generalised additive models)
Module 4 Habitat preference, Resource selection functions, MaxEnt: What’s it all about? Overview and caveats related to Niche models
Day 3: Challenging problems
Module 5 Analysing grid data, Poisson processes, Occupancy models, Use-availability designs
Module 6 Analysing telemetry data, Presence-only data, Spatial and serial autocorrelation, Partitioning variation by
mixed effects models
Day 4: Challenging problems
Module 7 Analysing transect data, Detection functions for point and line transects, Using covariates in transect models. Afternoon for catch up and/or excursion
Day 5: Challenging problems
Module 8 Advanced methods, Generalised Estimation Equations for difficult survey designs, Generalised additive
models for habitat preference, Dealing with boundary effects using soap smoothers, Spatial point processes with INLA
Day 6: Delivering advice
Module 9 Prediction, Validation by resampling, Generalised Functional Responses for species distribution, Quantifying uncertainty, Dealing with the effects of population density
Module 10 Applications, Designing protected areas, thinking about critical habitat, Representing uncertainty
Day 7: Hands-on problem solving
Module 11 Round table discussions, About 4 groups, each of 5-10 people working on a particular problem.
This 7 day course costs £630 for course only including lunch or £965 all inclusive, including all accommodation and meals.
Please email any inquiries to oliverhooker@prstatistics.com or visit our websitewww.prstatistics.com
Please feel free to distribute this material anywhere you feel is suitable
Upcoming courses – email for details oliverhooker@prstatistics.com
STABLE ISOTOPE MIXING MODELS USING SIAR, SIBER AND MIXSIAR USING R
ADVANCING IN STATISTICAL MODELLING USING R
TIMES SERIES DATA ANALYSIS FOR ECOLOGISTS AND CLIMATOLOGISTS
INTRODUCTION TO PYTHON FOR BIOLOGISTS
ADVANCES IN DNA TAXONOMY USING R
GENETIC DATA ANALYSIS USING R
MODEL BASED MULTIVARIATE ANALYSIS OF ECOLOGICAL DATA USING R
Dates still to be confirmed – email for details oliverhooker@prstatistics.com
INTRODUCTION TO R AND STATISTICS FOR BIOLOGISTS
APPLIED BAYESIAN MODELLING FOR ECOLOGISTS AND EPIDEMIOLOGISTS
LANDSCAPE (POPULATION) GENETIC DATA ANALYSIS USING R
PHYLOGENETIC DATA ANALYSIS USING R
BIONFROMATICS FOR GENETICISTS AND BIOLOGISTS
