Free

Introducing modern Generalized Additive Models

Event Information

Share this event

Date and Time

Location

Location

Room 1.08

Merchant Ventures Building

University of Bristol

Bristol

BS8 1UB

United Kingdom

View Map

Event description

Description

Generalized Additive Models (GAMs) models are an extension of traditional parametric regression models, which have proved highly useful for both predictive and inferential purposes in a wide variety of scientific and commercial applications. One reason behind the popularity of GAMs is that they strike an interesting balance between flexibility and interpretability, while being able to handle large data sets.

Workshop content

During this course we will explain what GAM models are, how they are estimated and how different smooth effects can be used for practical modelling. We will also show how to perform model selection, checking and visualisation using the mgcv and mgcViz R packages. The course will also explain how traditional GAMs can be extended to quantile GAMs, which are useful when the behavior of the mean response is not the main object of interest, and how these can be fitted using the qgam R package.

Hands-on session

In the hands-on sessions the attendees will use the above-mentioned R packages to model real data sets, pertaining to a variety of applications and scientific disciplines, such as electricity demand forecasting, quantitative Linguistics and Epidemiology.

Pre-requisites

The attendees should have a basic understanding of regression models and of the basic concepts underlying statistics and machine learning (e.g. probability densities, quantiles, etc). To get the most out of the hands-on sessions they should also have basic proficiency with the R language (eg. being able to load data and to fit a linear regression model).

This workshop is being sponsored by the Royal Statistical Society and run as part of University of Bristol’s Data Week.

For more info please email jgi-admin@bristol.ac.uk

Share with friends

Date and Time

Location

Room 1.08

Merchant Ventures Building

University of Bristol

Bristol

BS8 1UB

United Kingdom

View Map

Save This Event

Event Saved