A First Course in Statistical Programming with R

by W. John Braun, Duncan J. Murdoch

Overview

This third edition of Braun and Murdoch's bestselling textbook now includes discussion of the use and design principles of the tidyverse packages in R, including expanded coverage of ggplot2, and R Markdown. The expanded simulation chapter introduces the Box–Muller and Metropolis–Hastings algorithms. New examples and exercises have been added throughout. This is the only introduction you'll need to start programming in R, the computing standard for analyzing data. This book comes with real R code that teaches the standards of the language. Unlike other introductory books on the R system, this book emphasizes portable programming skills that apply to most computing languages and techniques used to develop more complex projects. Solutions, datasets, and any errata are available from www.statprogr.science. Worked examples - from real applications - hundreds of exercises, and downloadable code, datasets, and solutions make a complete package for anyone working in or learning practical data science.

Product Details

ISBN-13:	9781108995146
Publisher:	Cambridge University Press
Publication date:	05/20/2021
Edition description:	3rd Revised ed.
Pages:	280
Product dimensions:	7.40(w) x 9.65(h) x 0.59(d)

About the Author

W. John Braun is Professor of Statistics at UBC's Okanagan campus. His research interests are in the modeling of environmental phenomena, such as wildfire, as well as statistical education, particularly as it relates to the R programming language.

Duncan J. Murdoch is a Professor Emeritus and was a member of the R Core Team of developers and co-president of the R Foundation. He is one of the developers of the rgl package for 3D visualization in R, and has also developed numerous other R packages.

Table of Contents

Preface     ix
Getting started     1
What is statistical programming?     1
Outline of the book     2
The R package     3
Why use a command line?     3
Font conventions     4
Installation of R     4
Introduction to the R language     5
Starting and quitting R     5
Recording your work     6
Basic features of R     7
Calculating with R     7
Named storage     7
Functions     9
Exact or approximate?     9
R is case-sensitive     12
Listing the objects in the workspace     12
Vectors     12
Extracting elements from vectors     13
Vector arithmetic     14
Simple patterned vectors     15
Missing values and other special values     16
Character vectors     16
Factors     17
More on extracting elements from vectors     18
Matrices and arrays     18
Data frames     19
Dates and times     21
Built-in functions and online help     21
Built-in examples     22
Finding help when you don't know the function name     23
Built-in graphics functions     23
Additional elementary built-in functions     25
Logical vectors and relational operators     26
Boolean algebra     26
Logical operations in R     27
Relational operators     28
Data input and output     29
Changing directories     29
dump () and source ()     29
Redirecting R output     30
Saving and retrieving image files     31
Data frames and the read.table function     31
Lists     31
Chapter exercises     32
Programming statistical graphics     33
High-level plots     33
Bar charts and dot charts     34
Pie charts     35
Histograms     35
Box plots     36
Scatterplots     38
QQ plots     39
Choosing a high-level graphic     41
Low-level graphics functions     42
The plotting region and margins     42
Adding to plots     43
Setting graphical parameters     45
Chapter exercises      46
Programming with R     47
Flow control     47
The for () loop     47
The if () statement     50
The while () loop     54
Newton's method for root finding     55
The repeat loop, and the break and next statements     57
Managing complexity through functions     59
What are functions?     59
Scope of variables     62
Miscellaneous programming tips     63
Using fix ()     63
Documentation using #     64
Some general programming guidelines     65
Top-down design     67
Debugging and maintenance     72
Recognizing that a bug exists     72
Make the bug reproducible     73
Identify the cause of the bug     73
Fixing errors and testing     75
Look for similar errors elsewhere     75
The browser () and debug () functions     75
Efficient programming     77
Learn your tools     77
Use efficient algorithms     78
Measure the time your program takes     79
Be willing to use different tools     80
Optimize with care     80
Chapter exercises     80
Simulation     82
Monte Carlo simulation     82
Generation of pseudorandom numbers     83
Simulation of other random variables     88
Bernoulli random variables     88
Binomial random variables     89
Poisson random variables     93
Exponential random numbers     97
Normal random variables     99
Monte Carlo integration     101
Advanced simulation methods     104
Rejection sampling     104
Importance sampling     107
Chapter exercises     109
Computational linear algebra     112
Vectors and matrices in R     113
Constructing matrix objects     113
Accessing matrix elements; row and column names     115
Matrix properties     117
Triangular matrices     118
Matrix arithmetic     118
Matrix multiplication and inversion     119
Matrix inversion     120
The LU decomposition     121
Matrix inversion in R     122
Solving linear systems     123
Eigenvalues and eigenvectors     124
Advanced topics      125
The singular value decomposition of a matrix     125
The Choleski decomposition of a positive definite matrix     126
The QR decomposition of a matrix     127
The condition number of a matrix     128
Outer products     129
Kronecker products     129
apply ()     129
Chapter exercises     130
Numerical optimization     132
The golden section search method     132
Newton-Raphson     135
The Nelder-Mead simplex method     138
Built-in functions     142
Linear programming     142
Solving linear programming problems in R     145
Maximization and other kinds of constraints     145
Special situations     146
Unrestricted variables     149
Integer programming     150
Alternatives to lp ()     151
Quadratic programming     151
Chapter exercises     157
Review of random variables and distributions     158
Index     161

Editorial Reviews

"For what has come to be called data analytics, R is a remarkable tour de force. Strong skills with R programming are needed to allow really effective use. Mastering the content of this carefully staged text is an excellent starting point for gaining those skills."
John Maindonald, Australian National University

"This book should be especially useful for those without any prior programming background. The core programming material, such as loops and functions, is postponed to Chapter 4, allowing the student to first become comfortable with R in a broader manner. The placement of Chapter 3, on graphical methods, is particularly helpful in this regard, and is very motivating. The book is written by two recognized experts in the R language, so the reader attains the benefit of being taught by the 'insiders'."
Norm Matloff, University of California, Davis

"This book is an excellent introduction to programming in R. It gently takes the reader from first principles in programming through to more advanced topics such as simulation and plotting. We recommend this book to our graduate students in computational biology as a concise guide to learning R."
Stephen Eglen, University of Cambridge

From the Publisher