Understanding Regression Analysis: A Conditional Distribution Approach

Regression Analysis is a book that explains the conditional distribution model, which unifies diverse regression applications, and why the assumptions of the classical regression model are wrong. It takes a realistic approach that all models are just approximations and emphasizes modeling Nature's processes realistically. It features worked examples using R software, key points, self-study questions, mathematical explanations, statistical significance, probabilistic modeling, and simulations. It is ideal for research-oriented students in the social, biological, medical, and physical and engineering sciences, as well as a reference book for all scientists.

Format: Paperback / softback
Length: 514 pages
Publication date: 06 May 2022
Publisher: Taylor & Francis Ltd

Understanding Regression Analysis is a comprehensive guide that unifies diverse regression applications, including classical models, ANOVA models, generalized models such as Poisson, Negative binomial, logistic, and survival, neural networks, and decision trees, under a common framework: the conditional distribution model. This book explains why the conditional distribution model is the appropriate model and why the assumptions of the classical regression model are incorrect. Unlike other regression books, this one takes a realistic approach, recognizing that all models are approximations. Hence, the emphasis is on modeling nature's processes realistically rather than assuming that nature works in particular, constrained ways.

Key features of the book include:

Numerous worked examples using the R software: The book provides numerous worked examples using the R software, making it accessible to readers with a basic understanding of statistics.

Key points and self-study questions displayed just-in-time within chapters: Each chapter includes key points and self-study questions that help readers reinforce the concepts learned. These questions are displayed just-in-time, providing immediate assistance when needed.

Simple mathematical explanations (baby proofs) of key concepts: The book offers simple mathematical explanations of key concepts, ensuring that readers with a limited mathematical background can grasp the material easily.

Clear explanations and applications of statistical significance (p-values): The book provides clear explanations and applications of statistical significance (p-values), incorporating the American Statistical Association guidelines.

Use of data-generating process terminology rather than population-Random-X framework: The book assumes a data-generating process terminology rather than a population-Random-X framework, making it more applicable to real-world data analysis.

Clear explanations of probabilistic modeling, including likelihood-based methods: The book provides clear explanations of probabilistic modeling, including likelihood-based methods, which are essential for understanding and interpreting regression models.

Use of simulations throughout to explain concepts and perform data analyses: The book uses simulations throughout to explain concepts and perform data analyses, helping readers understand the practical applications of regression analysis.

This book has a strong orientation towards science in general, as well as chapter-review and self-study questions, making it suitable for research-oriented students in the social, biological, medical, and physical and engineering sciences. Additionally, its mathematical content makes it valuable for advanced students and professionals in the field.

In conclusion, Understanding Regression Analysis is a comprehensive and practical guide that provides a solid foundation in regression analysis for students and professionals in various fields. Its realistic approach, clear explanations, and extensive examples make it an invaluable resource for anyone interested in data analysis and statistical modeling.

Weight: 948g
Dimension: 254 x 178 (mm)
ISBN-13: 9780367493516