Modern Statistics

Modern Statistics: A Computer-Based Approach with Python is a course text that teaches modern statistics while using Python both as a teaching tool and as a working environment for analysis. Ron Kenett draws on years of classroom teaching, research, and hands-on work in industrial and applied settings, so theory is paired with practice throughout. Examples and case studies appear across the chapters, and several are worked through in detail with Python code.

A downloadable custom Python package, called mistat, lets readers reproduce the book's examples and try others of their own. The early chapters cover variability, probability models, and distribution functions. The book then moves to statistical inference and bootstrapping, followed by variability across several dimensions and regression models. Later sections address estimating finite population quantities through sampling and forecasting with time series analysis. The final two chapters survey modern data analytic methods.

Each chapter includes exercises, data sets, and applications. The book is intended for a one- or two-semester advanced undergraduate or graduate course. Because it lays a foundation, it can accompany any curriculum that requires data analysis, such as data science, industrial statistics, the physical and social sciences, or engineering. Researchers, practitioners, and data scientists can also use it for its applications and case studies.

A closely related companion volume, Industrial Statistics: A Computer-Based Approach with Python, covers statistical process control (including multivariate methods), experimental design (including computer experiments), and reliability (including Bayesian reliability). The two books can be used independently or for consecutive courses.