Regression is a set of statistical techniques widely used to analyse relationships between several variables.

The topics covered in this course include: linear regression; weighted least squares; generalized linear models (GLMs); fitting GLMs and examining model diagnostics; Poisson regression, binomial regression; analysis of variance; penalized regression methods; splines; penalized splines; thin plate splines; variable selection; generalized cross-validation; local likelihood; kernel smoothing; generalized additive models; multinomial logit analysis; ordinal logistic regression.

Lectures will be complemented with worked examples where students will perform data analysis and statistical programming using the R software.