Statistical Learning from a Regression Perspective

This textbook covers statistical learning applications, emphasizing the importance of sound data collection, management, and interpretation for accurate results. It discusses recent advances in statistical learning, including frameworks, big data, post-model selection inference, deep learning, and interdisciplinary ethical and political issues. It is written for upper undergraduate and graduate students in the social, psychological, and life sciences and researchers interested in applying statistical learning procedures to scientific and policy problems.

Format: Paperback / softback
Length: 433 pages
Publication date: 30 June 2021
Publisher: Springer Nature Switzerland AG

This comprehensive textbook delves into the realm of statistical learning, focusing on the conditional distribution of a response variable when predictors are available, and in the absence of a credible model that can be specified before data analysis commences. In alignment with contemporary data analytics practices, it emphasizes the importance of a holistic approach that encompasses robust data collection, efficient data management, appropriate statistical methodologies, and accessible interpretation of results. The central theme revolves around supervised learning, which is presented as a form of regression analysis. Key concepts and procedures are illustrated with numerous real-world applications and their corresponding code in the R programming language, with a strong emphasis on practical implications. The book also explores the growing intersection of computer science and statistics, highlighting the occasional but notable tensions that arise. Throughout, there are insightful links to the broader context.

The third edition of this textbook takes into account significant advancements that have occurred in recent years, including:

The emergence of overarching conceptual frameworks for statistical learning.
The profound influence of "big data" on statistical learning.
The nature and implications of post-model selection statistical inference.
The widespread adoption of deep learning in various forms.
The unique challenges posed by statistical learning to statistical inference.
The fundamental connections between data collection and data analysis.
The interdisciplinary ethical and political issues surrounding the application of algorithmic methods across diverse fields, each tied to concerns about transparency, fairness, and accuracy.

In addition to these updates, the third edition introduces new sections on accuracy, transparency, and fairness, as well as a comprehensive chapter on deep learning. This chapter provides a thorough exploration of this cutting-edge technology, its applications, and the ethical considerations associated with its use.

Precursors to deep learning are also discussed, providing a foundation for understanding the development and evolution of this powerful tool.

Overall, this textbook serves as a valuable resource for students, researchers, and practitioners interested in statistical learning, offering a comprehensive and up-to-date perspective on this rapidly evolving field.

Weight: 700g
Dimension: 235 x 155 (mm)
ISBN-13: 9783030429232
Edition number: 3rd ed. 2020