WK 5 - Fitting Non-Linear Models in R with the mgcv Package

Saturday, August 5, 2017: 8:00 AM-5:00 PM
A108, Oregon Convention Center
Organizer:
Noam Ross, EcoHealth Alliance
Co-organizers:
David L. Miller, Woods Hole Oceanographic Institution; Gavin L. Simpson, University of Regina; and Eric J. Pedersen, McGill University
To address the increase in both quantity and complexity of available data, ecologists require flexible models. This workshop will focus on on fitting generalized additive models (GAMs) - robust models for non-linear relationships - using the mgcv package for the R language.

mgcv is one of the most popular packages for modelling non-linear relationships. However, many users do not know how versatile and powerful a tool it can be. This workshop will focus on teaching participants how to use mgcv in a wide variety of situations (including spatio-temporal, zero-inflated, heavy-tailed, time series, and survival data) and advanced use of mgcv (fitting smooth interactions, seasonal effects, spatial effects, Markov random fields and varying-coefficient models).

The workshop will give paricipants an understanding of: (a) practical elements of smoothing theory in GAMs, with a focus on why they would choose to use different types of smoothers (b) model checking and selection (c) the range of modelling possibilities using mgcv. It will include both lecture and hands-on exercises. Participants should be familiar with R (loading/manipulating data, functions, and plotting) and regression in R (lm() and glm()). The organizers have extensive practical and teaching experience with ecological statistics and modelling using mgcv.

Registration Fee: $25

See more of: Workshops