GAM and zero-inflated models

Newburgh

2018

714 S.

Bandaufführung

978-0-9571741-4-6

18073BU

40002438

Thanks to the likes of Netflix, Amazon Video and Hulu we can now binge-watch a whole television series in one weekend. In front of you, you have Volume II of Beginner’s Guide to Spatial, Temporal, and Spatial- Temporal Ecological Data Analysis with R-INLA. Volume II, entitled GAM and zero-inflated models, is a continuation of Volume I. Volumes I and II consist of a total of 24 chapters. You can binge-read the whole thing in one weekend! There are analyses in Volume II that we could not perform 10 years ago, simply because the required software did not exist. Thanks to R (R Core Team (2018), R-INLA (Rue et al. 2009) and a large number of packages in R we can now easily apply generalised linear models (GLM), generalised additive models (GAM), generalised linear mixed-effects models (GLMM), and generalised additive mixed-effects models (GAMM) on count data, continuous data, proportional data, and their zero-inflated cousins, with spatial, temporal and spatial-temporal correlation. We can do this for geo-statistical data and for areal data. We can even deal with natural barriers like islands or coastlines. What was lacking was an explanation and illustration of these techniques for scientists not familiar with, or not interested in, detailed mathematics. There is where our two volumes fill a gap. The data sets that are analysed in this volume are all real data sets, and each data set comes with its own problems. Some of these data sets were a major challenge even for statisticians to analyse. Yet, they are typical of what biologists tend to sample.