Short Courses

Extended mixed effects regression modelling

Michael J. Crowther (University of Leicester, UK)

Course description

The merlin package can do a lot of things. From simple linear regression to a spline-based survival model, from a three-level logistic model, to a multivariate joint model of multiple longitudinal outcomes, a recurrent event and survival. merlin can do things I haven’t even thought of yet. It’s a flexible framework for modelling any number of outcomes (each of any type), with any number of levels, and any number of random effects at each level, allowing for simple or complex non-linear effects, extended linking between outcome models, and much more. Merlin is easily extended by the user, providing a platform for methodological and software development. In this half-day course, I will take a single dataset of patients with primary biliary cirrhosis and show you the range of merlin’s capabilities. The course will consist of lectures and practical exercises, which will be provided in both Stata and R.

Further details and examples of merlin can be found here: www.mjcrowther.co.uk/software/merlin

Investigating Spatial Heterogeneity with Geographically Weighted Models

Paul Harris (Rothamsted Research, UK) and Chris Brunsdon (Maynooth University, Ireland)

Course description

Spatial statistics is an ever-expanding discipline providing analytical techniques for a wide range of disciplines in the natural and social/economic sciences. In this workshop, we’ll outline techniques from a particular branch of spatial statistics, termed geographically weighted (GW) models. GW models suit situations when data are not described well by some global model, but where there are spatial regions where a localised calibration provides a better description. The approach is moving window based, where localised models are found at target locations calibrated with weighted data subsets. Outputs are mapped and spatially-interrogated to provide insight into the nature of the data’s spatial heterogeneity. Core GW techniques include: GW summary statistics, GW principal components analysis, GW regression, GW generalised linear models and GW discriminant analysis (Gollini et al. 2015; JSS 63(17):1:50). This workshop will focus on GW regression, illustrated with applications in agriculture.

Design of Multifactor Experiments in Biological Research

Steven Gilmour (King's College London, UK)

Course description

Factorial design structures are the most efficient way to answer multiple questions in experimental studies and have a long history of successful application in biology. Many modern experiments require design structures that are more complex than simple factorial or regular fractional factorial designs and in this course we will explore some of these. In particular, we will cover: recent methods for multi-objective optimal design; classical and optimal response surface designs; nonlinear response surface models; and multi-stratum designs, in which some factors have levels which are more difficult to set than others. Methods will be described and applications to a range of biological applications will be illustrated.