The advent of R software has had a significant effect on teaching, research, computation and data analysis in statistics in the last decade. As it is free software it has motivated researchers to develop their own packages and have them distributed freely through www.rproject.org. In turn, it has changed the style of teaching for instructors as well as the use of statistical software for users and researchers. The present book is the second edition with the first edition published in 2004 with a view to establish an interface between the foundation of statistical concepts in theory and their data application by using S-PLUS and SAS software. It undoubtedly filled a need of that time. Due to increased popularity of R, the second book has been heavily revised and is now based on the use of R software. The author, Professor Burt Holland, died in 2010 and so the revision has been done by Professor Robert M. Heiberger but the presence and voice of Professor Holland in the current version is acknowledged in the preface.

The book is developed in 18 chapters. Each chapter describes the theoretical details of the topics followed by the commands and steps for its implementation and execution in R software. Chapter 1 briefly presents an introduction with examples and motivates the reader with the utility of statistics. Chapter 2 details the basic concepts and definitions related to data. Chapter 3 describes various basic statistical concepts related to probability, graphical presentation, distributions, estimation, testing of hypotheses and sampling techniques. Next Chapter 4 discusses various types of graph. Chapter 5 introduces the basic concepts of point and interval estimation of parameters along with tests of hypotheses in parametric and non-parametric settings. Chapter 6 describes the basics of one-way analysis of variance in fixed and random-effect models. Various multicomparison test procedures and related concepts are explained in Chapter 7. The next four chapters 8–11 deal with the topics of linear regression analysis and detail the theoretical developments in simple regression, multiple regression, dummy variable models and analysis of covariance. The next three chapters 12–14 present the theoretical construct of the topics on two-way analysis of variance, factorial designs, confounding and fractional factorials. Chapter 15 concerns the statistical tools for bivariate discrete data and Chapter 16 illustrates non-parametric statistical procedures. Chapters 17 and 18 explain the topics of logistic regression and time series analysis respectively. There are 14 appendices which explain different topics in R related to its implementation and handling in different settings. Such knowledge is required for the understanding and implementation of the procedures that are described in earlier chapters.

An important strength of this book is that it details first the solid theoretical statistical foundation of the topics. Then it presents step-by-step commands for implementing the procedures by using data sets and has a detailed discussion of the output. This helps the reader to develop a better understanding between a concept and its implementation in R. Several fully solved examples have been adopted in each chapter to help the reader to better understanding. Most of the important topics in applied statistics have been included in the book. Various interfaces of R with other software and computing platforms are clearly detailed. The language of the book is simple and easy to understand. Since the fundamentals are presented followed by computations, therefore it is also easy for a beginner to follow this book.

Compared with the first edition of this book in 2004, there is not much change in the coverage of theoretical content and the chapters are the same. The earlier edition was based on the use of S-PLUS and SAS software whereas the present edition is based on the use R software. Graphics have been obtained in colour which enhance the clarity of visualization and improve understanding. New graphics have been added at various places, which give more insight into the solutions. A few topics in some chapters have been added; for example Chapter 10 includes analysis of covariance, Chapter 11 now has a discussion on residuals and leverage, Chapter 15 also has now a section on Likert scales and so on. The changes are mainly with respect to computation, commands and graphics. Most of the examples are also the same as in the first edition but they have been reillustrated by using R. The distinction between the first and second editions of the book is clear—those who want to use S-PLUS and SAS need to consult the first edition and those using R need to consult the second edition.

This article is published and distributed under the terms of the Oxford University Press, Standard Journals Publication Model (https://academic.oup.com/journals/pages/open_access/funder_policies/chorus/standard_publication_model)