Regression, nonlinear and GLMs

Course details

Who Should Attend Some familiarity with GenStat is necessary (for example from an Introductory GenStat Course). You should also be aware of the standard probability distributions (Normal, binomial and Poisson), but there will be no need for any complicated maths. On each day the lectures will be interspersed with practicals to introduce you to real-life data sets and illustrate the methods. The practicals also give you the opportunity to discuss your own problems and investigations with the presenters.
Duration 2 days
Overview Regression is one of the most widely used methods in statistics, and one that is still producing new and exciting techniques. This 2-day course starts by explaining ordinary linear regression (with one or several variables), and then extends the ideas to nonlinear models and on to generalized linear models – so that you can analyse counts and proportions as well as the more usual numeric variables. The final session will introduce some of the most recent developments in generalized linear models, including Youngjo Lee and John Nelder’s hierarchical generalized linear models, to bring you fully up-to-date with the range of possibilities.
Learning Objectives GenStat has a very powerful set of facilities for regression and generalized linear models that are nevertheless very straightforward and easy to use. The course is designed to familiarize you with these techniques, and give you the underlying knowledge and confidence to use them correctly and effectively. It shows how GenStat’s menus guide you from simple even to very complicated analyses, and also explains the regression commands to enable you to program any non-standard analyses that you need.
Methods of Evaluation Subsequent to instructor facilitated sessions, participants will be expected to complete example analyses and exercises unaided.
Training Methods Instructor facilitated, interactive computer sessions.
Contents The Course is in 4 sessions:

  1. Linear regression Ranging from simple linear regression (with one variable) to multiple linear regression (several variables) and the modelling of parallel-line relationships (regression models with groups); plotting of residuals to assess the assumptions, and of the fitted model and data to assess the fit; methods for finding the best models when there are many explanatory variables.
  2. Nonlinear models GenStat’s range of standard curves, and the facilities for defining your own nonlinear models.
  3. Generalized linear models How to analyse non-Normal data such as counts and proportions.
  4. Recent advances in generalized linear models How to use generalized linear mixed models and hierarchical generalized linear models to handle additional sources of random variation.

Contact us

For further information about this course or on-site training, please email the training team or call them on +44-(0)1442-450230.