Part of the OpenIntro project, this introductory statistics textbook by Mine Çetinkaya-Rundel and Johanna Hardin takes a modern approach to the first course in statistics. It reimagines the earlier Introductory Statistics with Randomization and Simulation and introduces multivariable thinking early, with a strong emphasis on exploratory data analysis through visualization, summary statistics, and descriptive models.
Inference is introduced first through simulation, using randomization tests and bootstrapping, and only then connected to traditional methods based on the Central Limit Theorem.
The main text does not depend on any particular software, but each part is paired with interactive R tutorials and data analysis labs built on the tidyverse and the infer package, and most datasets live in the openintro package.
The second edition brings updated datasets, additional exercises, a new application in the data chapter, and text and code revised to reflect current best practices.
The book is organized into six parts:
- Introduction to data, including study design
- Exploratory analysis of categorical and numerical data
- Regression modeling with one or more predictors, plus logistic regression
- Foundations of inference: randomization, bootstrapping, mathematical models, and decision errors
- Statistical inference for proportions, two-way tables, and means
- Inferential modeling for linear and logistic regression
Each part closes with an applications chapter that ties the ideas together. The book is free to read online, available as a pay-what-you-want PDF, and sold as an affordable paperback.
Find out more about the book and the supplementary resources at openintro.org/book/ims.
