1st Edition

# Computational Statistics An Introduction to R

274 Pages 12 Color Illustrations
by Chapman & Hall

264 Pages
by Chapman & Hall

Also available as eBook on:

Suitable for a compact course or self-study, Computational Statistics: An Introduction to R illustrates how to use the freely available R software package for data analysis, statistical programming, and graphics. Integrating R code and examples throughout, the text only requires basic knowledge of statistics and computing.

This introduction covers one-sample analysis and distribution diagnostics, regression, two-sample problems and comparison of distributions, and multivariate analysis. It uses a range of examples to demonstrate how R can be employed to tackle statistical problems. In addition, the handy appendix includes a collection of R language elements and functions, serving as a quick reference and starting point to access the rich information that comes bundled with R.

Accessible to a broad audience, this book explores key topics in data analysis, regression, statistical distributions, and multivariate statistics. Full of examples and with a color insert, it helps readers become familiar with R.

Introduction
Basic Data Analysis
R Programming Conventions
Generation of Random Numbers and Patterns
Case Study: Distribution Diagnostics
Moments and Quantiles
Regression
General Regression Model
Linear Model
Variance Decomposition and Analysis of Variance
Simultaneous Inference
Beyond Linear Regression
Comparisons
Shift/Scale Families and Stochastic Order
QQ Plot, PP Plot, and Comparison of Distributions
Tests for Shift Alternatives
Power and Confidence
Qualitative Features of Distributions
Dimensions 1, 2, 3, …, infinity
Dimensions
Selections
Projections
Sections, Conditional Distributions, and Coplots
Transformations and Dimension Reduction
Higher Dimensions
High Dimensions
Appendix: R as a Programming Language and Environment
Help and Information
Names and Search Paths
Basic Data Types
Output for Objects
Object Inspection
System Inspection
Complex Data Types
Accessing Components
Data Manipulation
Operators
Functions
Debugging and Profiling
Control Structures
Input and Output to Data Streams; External Data
Libraries, Packages
Mathematical Operators and Functions; Linear Algebra
Model Descriptions
Graphic Functions
Elementary Statistical Functions
Distributions, Random Numbers, Densities …
Computing on the Language
References
Functions and Variables by Topic
Function and Variable Index
Subject Index
R Complements, a Statistical Summary, and Literature and Additional References are included with most chapters.

### Biography

Gunther Sawitzki (Author)

… instructors will find lots of interesting material to use in a variety of courses. In addition, most non-expert users of R will enjoy reading the book and learn a few things they did not know before.
—T. Mildenberger, Statistical Papers, July 2011

For those who want to learn R and have a good statistics background, this book is a good choice. … the book is quite valuable and I am very glad that I have acquired a copy.
—David Booth, Technometrics, August 2010

… a fresh perspective on teaching statistics. … The book introduces its topics and the corresponding methodologies well. … the book is well put together and quite enjoyable for its purpose of serving a small course on computational statistics. …
Journal of Statistical Software, December 2009

… a well-written and nicely organized book suitable for quantitatively and computationally sophisticated readers. … it is the integration of interesting examples and associated R code that make the text a pleasure to read and work through. The examples are neither overly trivial … nor excessively complicated, and the R code is similarly accessible without being either too simple or complex. … Computational Statistics: An Introduction to R will be most useful to computer savvy readers with at least some skill in statistical programming who would like a succinct introduction to R. It could also be useful as a supplementary text for upper-level undergraduate or graduate courses with labs that use R. …
—Ronald D. Fricker, Jr., The American Statistician