Regression with R and Python

Beschreibung

Regression with R and Python is a modern applied textbook on regression analysis that integrates theory, interpretation, and hands-on implementation in both R and Python. The guiding principle is that the meaning of a regression coefficient depends on the goal of the analysis—descriptive, predictive, or causal—so the book emphasizes interpretation first and clarifies which assumptions are needed, for which conclusions.

The core chapters build from covariation and simple linear regression to multiple regression, functional form, and inference under clustered and panel-type dependence. The book then covers binary dependent variables and maximum likelihood estimation, modern prediction workflows (train/test splits, cross-validation, regularization, and tree-based methods), nonparametric regression, time-series regression and forecasting, and causal inference designs (experiments and key quasi-experiments such as difference-in-differences, instrumental variables, and regression discontinuity). A dedicated appendix develops robust inference for correlated error terms, including HAC/Newey-West, fixed-b, and self-normalization methods. Details on inference with nonparametric regression are developed in a separate appendix.
Two programming appendices provide a self-contained introduction to R and Python and mirror the workflow used in the chapters. Additional appendices collect mathematical tools and give matrix-based technical presentations of OLS, GLS, and IV/2SLS.
This book is intended for advanced undergraduate and early graduate students in statistics, econometrics, data science, and applied social sciences. Prerequisites are an introductory statistics course and basic calculus and algebra. Basic programming experience is helpful but not required.

Regression with R and Python is a modern applied textbook on regression analysis that integrates theory, interpretation, and hands-on implementation in both R and Python. The guiding principle is that the meaning of a regression coefficient depends on the goal of the analysis—descriptive, predictive, or causal—so the book emphasizes interpretation first and clarifies which assumptions are needed, for which conclusions.
The core chapters build from covariation and simple linear regression to multiple regression, functional form, and inference under clustered and panel-type dependence. The book then covers binary dependent variables and maximum likelihood estimation, modern prediction workflows (train/test splits, cross-validation, regularization, and tree-based methods), nonparametric regression, time-series regression and forecasting, and causal inference designs (experiments and key quasi-experiments such as difference-in-differences, instrumental variables, and regression discontinuity). A dedicated appendix develops robust inference for correlated error terms, including HAC/Newey-West, fixed-b, and self-normalization methods. Details on inference with nonparametric regression are developed in a separate appendix.
Two programming appendices provide a self-contained introduction to R and Python and mirror the workflow used in the chapters. Additional appendices collect mathematical tools and give matrix-based technical presentations of OLS, GLS, and IV/2SLS.
This book is intended for advanced undergraduate and early graduate students in statistics, econometrics, data science, and applied social sciences. Prerequisites are an introductory statistics course and basic calculus and algebra. Basic programming experience is helpful but not required.

Autor*in

Per Johansson

Themen in »Regression with R and Python«

Econometrics Statistical inference Causal inference Prediction Time series R Python Regression analysis

Stimmen zu »Regression with R and Python«

“This is a rare regression textbook that treats description, prediction, and causal inference as genuinely distinct tasks requiring different assumptions, rather than three flavours of the same exercise. The treatment of nonparametric regression is a particular highlight: intuitive, rigorous where it needs to be, and directly connected to modern applications like regression discontinuity design.” (Oliver Linton, University of Cambridge)

“Regression with R and Python is a wonderful and inspiring guide to learning from data rather than merely processing it. It shows how the proliferation of data becomes valuable only when statistical reasoning transforms information into knowledge. Its great strength is the learning path: from description and visualization, through prediction, to causal reasoning and credible empirical conclusions. R and Python turn this path into an active experience in which readers reproduce, modify, and extend real analyses. The book thereby connects data analytics with understanding: computation serves interpretation, rather than replacing it. Different learning depths—from intuitive applications to advanced technical material—allow readers to construct their own route through the subject. A timely book that teaches not only how to analyse data, but how data become knowledge.” (Wolfgang Karl Härdle, Humboldt-Universität zu Berlin)

“This is a comprehensive and up-to-date introduction to regression, one of our most powerful econometric tools. The presentation is self-contained, with a concise overview of relevant stats, math, and an accessible introduction to two modern open-source programming languages. In combination with crystal-clear videos, the book is sure to be a hit with students and practitioners alike.” (Joshua Angrist, Massachusetts Institute of Technology)

Details

Link teilen