This ever-popular annual 2-part course provides instruction in advanced methods in veterinary epidemiology.
Module 1, entitled “Spatial Data Management And Geoprocessing Using Open Source Tools”, was held July 5–8, 2011. Course Instructors were Dirk Pfeiffer, Dr Med Vet, MACVSc, PhD DipECVPH, Professor of Veterinary Epidemiology, at The Royal Veterinary College, University of London, and Javier Sanchez, DVM, PhD, CFIA Research Chair- Risk Analysis, Canadian Regulatory Veterinary Epidemiology Network, Atlantic Veterinary College.
The goal of the 4 day course was to provide a practical guide for handling spatial data using open-source software, to allow participants to develop a set of skills to manipulate spatial information. The participants were provided with basic concepts of geographical information systems and spatial epidemiology such as spatial data representation, different types of spatial information, and a short introduction to spatial data analysis.
The course focused on the practical aspects of data management, data processing and data visualization of the main types of spatial data: point patterns, aggregated and continuous spatial data using open source software. The main software used was be Quantum GIS, including some of its main add-in applications, and other open-source tools were also briefly introduced.
Module 2 was a 5 day course held July 10 – 14, 2011, entitled “Introduction To Multilevel Modelling”. Instructed by Ian Dohoo, DVM, PhD, FCAHS, Professor – Epidemiology; Director, Centre for Veterinary Epidemiological Research, Atlantic Veterinary College and Henrik Stryhn, PhD, MSc, Associate Professor-Biostatistics, Atlantic Veterinary College.
The course was designed to provide participants with the knowledge and skills required to successfully fit multilevel models to both continuous data (linear models) and discrete data (emphasis on logistic and Poisson models). The presentation of theoretical background material was limited to that which is required for a reasonable understanding of the methods employed.
Specific topics covered in the course included: introduction to multilevel/hierarchical data, mixed models for continuous data, mixed models for discrete data, model evaluation (diagnostics), analysis of repeated measures and alternative approaches to dealing with clustered data (including Bayesian methods). The main software used for the instruction was MLwiN, but code for fitting models in additional software packages (including Stata) were also provided.
A truly international group gathered at UPEI for the 2 modules in early July. Two dozen participants represented several countries including Canada, USA, Norway, Taiwan, Singapore, New Zealand, Brazil, Puerto Rico, Ireland, Austria, Bolivia, and Bhutan.