Generalized Additive Models for Location, Scale and Shape: A Distributional Regression Approach, with Applications

Distributional regression is a developing area of statistics that enables the modelling of the full conditional distribution, and this book introduces generalized additive models for location, scale, and shape (GAMLSS). It discusses penalized likelihood inference, Bayesian inference, and boosting as potential estimation methods and showcases their application in complex applications through case studies. The R code and data sets for the case studies are available on the book's companion website.

Format: Hardback
Length: 306 pages
Publication date: 29 February 2024
Publisher: Cambridge University Press

Distributional regression is a rapidly evolving field in statistics that enables the modeling of the entire conditional distribution, rather than just the mean. This comprehensive book introduces generalized additive models for location, scale, and shape (GAMLSS), one of the most significant classes of distributional regression. With a broad perspective, the authors explore various estimation methods, including penalized likelihood inference, Bayesian inference, and boosting, and illustrate their practical applications in complex scenarios. Written by an international team that pioneered GAMLSS, the text emphasizes practical questions and problem-solving, setting it apart from other statistical literature. Case studies showcase how researchers from statistics and other data-rich disciplines can utilize the model to address real-world problems, ranging from fetal ultrasounds to social media performance metrics. The book provides R code and data sets for the case studies, allowing readers to replicate and further investigate the topics covered. This resource is an invaluable tool for anyone interested in advancing their knowledge and expertise in distributional regression and its applications.

ISBN-13: 9781009410069