Modern Applied Statistics with S (Fourth Edition) is one of the oldest and most popular books on Applied Statistics using R and S-plus. A large number of topics in Applied Statistics are covered in this book and it is certainly not for the faint hearted. A sound knowledge of the Statistical Methods covered in each Chapter is important and there are the book includes many examples of using a wide range of techniques.

The book opens with an overview of the S programming language and has an introductory analysis session to get the reader into using the system and to provide an idea of the way analysis is undertaken and some of the methods that are available to the analyst.

The second Chapter introduces objects, which are an important part of the S programming language and the chapter covers a number of common data manipulation tasks and also the data frame which is probably the most useful object for the user. A brief coverage of data import and export follows and could possibly benefit from providing some more examples rather than focussing on describing the function arguments. There is a nice little section of working with subsets of data frames which is an important topic for analysis. The chapter ends well on creating tables and cross-tabulation of data.

The third Chapter is an overview of the S programming language and provides some good examples and sensible advice about the need to make use of the vectorised calculation features of the language rather than using loops. This is a neat feature of the S language that is very important for users to get to grips with as it will simplify and speed up code. There will of course be situations where loops are required but overall it is best to avoid then where possible. There is only a small section on classes and methods and this is probably due to the authors having a separate book that describes S programming.

Chapter four covers the base graphics system as well as Trellis graphics. This is a very good chapter that provides a large range of examples of common types of displays and highlights investigating multivariate data using the Trellis graphics paradigm. The many code examples can be adapted by the reader to create displays that are suitable for a specific application. There could have been more information about editing various components of the graphs but that would probably have been outside the scope of the book.

The fifth chapter provides coverage of a range of univariate statistical methods starting with probability distributions and generating pseudo random numbers from the range of distributions available in R. There follows a good section of histograms and the issue of bin widths which are important for getting a good idea of the shape of a set of data. Classical statistical tests are given very short coverage compared to other books but there is enough for people to get started with other tests. There is a good little section of robust statistical methods which is a topic that is infrequently covered in other texts. Density estimation is also covered and the chapter ends with examples of using the bootstrap for statistical inference.

Linear models are covered in chapter six starting with a reasonably simple example going through fitting models, checking the goodness of fit with residual diagnostics and making predictions from a linear model. There is a good little section on robust regression showing the ease of moving between models of different types. This is followed by an illustration of applying the bootstrap to parameter estimation in a linear model. Fitting analysis of variance models is covered with an example from a designed experiment which then leads to variable selection. The chapter ends with a short discussion of multiple comparison tests and post-hoc testing.

Generalized linear models (GLM) are covered in brief in chapter seven of the book starting with a couple of examples of logistic regression for binary data and then Poisson regression for data that is based on counts. The chapter provides some other useful examples but is rather short given the other potential distributions for different data sources.

In chapter eight non-linear models which often arise from theoretical considerations are investigated with details of how to fit them to data and to analyse the model outputs to determine the suitability of the model. The various issues associated with non-linear models due to the requirement for an iterative method to converge to a solution and discussed in detail along with methods for investigating the suitability of the assumptions. The second half of the chapter a wide range of extensions/alternatives to multiple linear regression covering smoothers, additive models, MARS, projection pursuit regression and neural networks. This provides a taste rather than a comprehensive coverage of these topics which is a general theme of the book.

Tree based methods are introduced and discussed in chapter nine and the technical details are covered in more detail than some of the other methods which may be beyond the interest of some readers. The authors do however then move swiftly on to practical applied examples showing how to fit tree models to data and suggestions on how to simplify tree models to a manageable size.

The tenth chapter of the book is dedicated to mixed effects models which is a framework that allows a standard linear or non-linear model to include a mixture of fixed and random effects. The focus is mainly on the nlme package which is in frequent use by analysts using R or S-plus for their work. The authors make a good effort at explaining the use and interpretation of these models which is a good starting point for the Pinheiro and Bates book on Mixed Effects Models that covers the topic in greater detail. Generalized Linear Mixed Effects Models are covered briefly at the end of the chapter.

The broad area of exploratory multivariate analysis is addressed in chapter eleven starting with the some projection techniques – from the popular principal component analysis to projection pursuit and multidimensional scaling. Next up are partitioning methods including cluster analysis used for searching for structure in data set where there is no prior information about grouping. The chapter is rounded off with a discussion of techniques that are suitable for discrete data, often in the form of a contingency table, such as mosaic plots to investigate association between variables measured in a study.

The topic of classification using statistical methods is covered in chapter twelve of the book. The chapter starts with discriminant analysis, which is one of the initial techniques used for classification, and touches on robust estimation of means and variances (location and scale) which is used to reduce the impact of unusual data points. There is then coverage of other methods used in classification such as K-means, neural networks and support vector machines. The performance of the competing methods is compared with an example on foernsice glass at the end of the chapter.

Chapter thirteen is devoted to survival analysis and covers different approaches to handling survivor curves such as the Cox Proportional Hazards Model with a couple of extensive examples to illustrate the different models. As with most chapters in the book an assumption is made with regards to knowledge of the statistical methods discussed in the text.

Time series analylsis is the topic of interest in chapter fourteen starting with the important topics of autocorrelation functions and partial autocorrelation functions. The frequently used ARIMA models are discussed next with a short discussion of model selection for these models and forecasting future values. Seasonality is also covered as would be expected. The chapter ends with short sections on regression with autocorrelated errors and analysis of financial time series.

Chapter fifteen is a short chapter on spatial statistics with three areas covered – spatial interpolation and smoothing, kriging and point process analysis. There are worked examples showing how to undertake the analysis using S and is more of a useful reference for people who understand the theory but need instructions on how to apply the methods.

The final chapter is on functions for performing general optimisation tasks and is slightly out of place compared to many of the other chapters. It is a useful topic but it is not clear how easy the reader will find it to make use of the methods based on the coverage in this chapter.

Overall comment: this is a very good book (and highly recommended book) but probably not ideal for the beginner as it covers a very wide range of applied statistics methods and is probably best as a reference book to be dipped into as and when necessary. It does however provide a nice overview of the range of statistical applications and modern methods.

This book is written by the author of the ggplot2 package for R, which is a package with a design inspired by the grammar of graphics and can remove some of the effort required to put together impressive graphs. The book is just under 200 pages and covers a decent range of material to introduce new and experienced R users to the ggplot2 package.

The first chapter is a short introduction to the ggplot2 package and discusses how it fits in with the other approaches to creating graphics in R.

The second chapter covers usage of the qplot function and is intended to allow people to hit the ground running. As mentioned by the author a large amount of functionality is available through this function and it shields the inexperienced users from the full details of the grammar of graphics. The running example using data on diamond quality covers various common components of a graphical displays that most users would be interesting in reading about. The chapter is a good introductory tour of the facilities available with ggplot2.

Chapter three moves from using qplot to the ggplot function for creating graphics and the concept of adding components to the graph by the + operator, and the nice feature that a graph can be saved as an object and added to at a later day piece by piece. The automatic creation of legends is one area where ggplot2 scores highly compared to other graphics system although it will not be clear to novice users how to fine tune various aspects of the display – though it is questionable whether they should be tweaking ever last detail.

The next chapter (four) condesense a large amount of information about the layers that are used to make up different display types into a short space via tables. The concepts of geoms and stats are important for the system and the chapter might possible be best read after working through other examples in the book.

Chapter five, titled the toolbox, discusses a wide range of graphics that a user might be interested in creating ranging from distributions to surface plots providing a good description and reference point for determining how to create the type of graph of interest. The chapter continues the process of demonstrating how to build plots up layer by layer using the grammar of graphics approach.

In chapter six there is a long and detailed coverage of the setting up the axis scales and how to customise them to avoid over plotting with too many numbers of the axes as well as transformations such as logarithms which are commonly used in various applications. The chapter ends with a discussion of the automatic creation of legends by ggplot2 and highlights the fact that not having too much control over the appearance simplifies creation of a legend rather than introducing undesirable restrictions on the user. In most cases the defaults will be sufficient and compared to other graphics approaches in R is something to be applauded.

The use of facets is covered in chapter seven which is the equivalent of trellising in the lattice graphics. There are some good examples provided to show how to create facets with one or two variables and coverage of working with scales and axes over multiple facets.

Chapter eight provides a brief summary of the use of themes to determine the visual style of ggplot2 graphs and also discusses exporting graphs to be included in documents outside of R. This chapter might benefit form more examples of customising the themes as this is an area where people might want to know how to do more. In chapter nine there is a short introduction to another package created by the author of ggplot2, the plyr package for manipulating data more easily than with standard R approaches. There is a good example for plotting fitted models on top of data and including confidence limits on the graph as well.

The book ends with a short chapter ten providing a few tips on reducing duplication when coding in R and feels slightly out of place.

Overall Comment: This is a well presented book that provides a good introduction to the ggplot2 package for R and is a good compliment to the online help provided by the author.

This book covers interactive graphics and their role in data analysis and covers the GGobi software package, which is an open source project for data visualisation, and the book is written by the two authors as well in addition to the R statistical environment.

Overall this is a nice introduction to the data analysis and graphical methods to support such analysis and the book doesn’t try to cover too much information. This is possibly a reflection on the scope of GGobi which has been designed for some specific tasks and written so that it can be linked to other software such as R rather than a bloated system with far more functionality that is required for a specific application.

The book starts with an introductory chapter that gently works through an example using tipping data from a restaurant. Graphs are produced and discussed in the text to show how they relate to the thought process of the authors when undertaking their analysis. The chapter ends with a short piece describing moving from static to interactive analysis and how this can benefit an analysis.

The second chapter, titled the Toolbox, covers the types of graph that are available for different data and focusses primarily on GGobi but mentions other types of plot that are available in R to compliment the tools available in GGobi. One main feature of GGobi that does not appear in many packages is the tour that is based on linked different interesting projections of variables to study what projection provides separation between the data. This is a useful activity for pattern recognition where we have a supervised problem with known classes and want to investigate how to use the variables in our data set to discriminate between the classes. Brushing is also discussed as a technique to link multiple plots, so we might want to focus on one subset of the data and see what values this group has for the variables in the data.

The third chapter is a short look at missing data, which is a problem encountered by all data analysts on a regular basis and in particular when we are working with large multivariate data sets. The chapter touches briefly on data imputation to fill in the gaps so that we can use the whole data set for any multivariate analysis. Overall the chapter is a short introduction to the area rather than a comprehensive coverage.

In chapter four the authors discuss supervised classification methods starting with parametric methods, such as Fisher’s linear discriminant analysis and then more recent algorithmic methods from fields such as data mining which are more black box methods. There is a good introduction to using graphical methods only to get an initial idea of class structure (groups) within the data and separation of the data into these classes using one or more of the recorded variables. The chapter then moves on to combine graphical displays with numerical output from the classification algorithms to get a broader picture of how well a method describes a particular set of data. Tree methods are introduced and their benefits including interpretation based on a number of decision points compared to the black box methods of neural networks or support vector machines that are also touched on in the chapter.

Chapter five provides coverage of cluster analysis, which of one of the techniques used during unsupervised classification. There is a nice display of graphs showing the process of identifying potential clusters in a data set shown near the start of the chapter, which provides an insight into how the authors would undertake this type of analysis. Numerical techniques for cluster analysis are then covered as a formal approach to identifying potential clusters based on numeric metrics. Output from the techniques is shown with colour graphs to highlight the clusters identified in the analysis.

In chapter six various unconnected ideas are discussed to cover some other topics like longitudinal data or multidimensional scaling which might be of interest to the reader.

The book ends with a chapter discussing the data sets that are available with GGobi.

Overall comment: this is a reasonably short but very readable introduction to exploratory data analysis using graphical methods. Various methods are illustrated well with colour graphics to provide an insight into how to analyse data at the start of an investigation prior to any model building activities.

This book by Deepayan Sarkar, who is the author of the lattice package for R, provides an introduction to this implementation of the trellis graphics system followed up with a large range of examples of frequently used graphics. The book is divided into three parts starting with the basics leading into taking greater control of the graphics systems and finishing with a brief discussion of extending the lattice library.

Overall the book is easy to read and there are many examples covering different types of display and the author has a website where the different figures can be browsed, which is a good online complement to the book. Many of these examples are based on multi-panel displays which is one of the strengths of Trellis graphics to allow multivariate data to be investigated with lower dimensional plots.

Part I starts with an overview of using lattice to produce graphical displays of some of the frequent used data sets for teaching R. These examples show how patterns in multivariate data can be visualised on a static display. There are a couple of examples based on stack bar charts which are not easy to compare groups when compared to a dot plot and are characteristic of the chart junk produced by various other software systems. The next chapter looks at summarising univariate data and provides a reasonable coverage of the standard graph types – including box and whisker, density plot, histogram and quantile-quantile plots.

Chapter 4 considers tabular data and types of graphs that are alternatives to histograms or bar charts. The dot plot is a display introduced by Cleveland that is more effective than a bar chart for comparing data and this chapter does a good job at demonstrating the benefits of dot plots.

Chapter 5 concentrates on scatter plots and shows different ways to visualising groups within a data set. This can be done by grouping the data using different symbols or colours within a panel or by conditioning the data on one or more of the variables. Scatter plot matrices are introduced at the end of the chapter as a good way to explore multivariate data by looking at pairwise plots of the variables and lastly parallel coordinate plots are introduced. These are not particularly useful displays as the message show to the viewer depends on the order the variables in the plot.

Part I concludes with a chapter on three dimensional displays which are always challenging to produce on a two dimensional computer display or printed page. Some examples of the different types of surface are shown, both three dimensional as well as contour plots. There are then some examples illustrating trellis displays with a surface in each panel which tie in nicely with the trellis philosophy of visualising high dimensional data.

Part II provides details of how the user can adjust some of the lattice parameters to customise the graphical display.

Chapter 7 provides a good overview of the graphical parameters that can be set in a trellis theme and which types of display make use of the different types of parameter. These include the types of plot symbol, size of the symbol, colour etc. Chapter 8 continues the look at the visual display covering first axis labels in detail followed by aspect ratios. Chapter 9 considers various types of labels that can be applied to a graph, such as titles or axis labels. There is also a good section on creating legends for trellis displays.

Chapter 10 covers miscellaneous topics associated with converting data into a suitable format for using lattice graphics, which is an area which is often neglected and is a good addition to the book. The use of shingles to create categories from a continuous variable is also covered – this is equivalent to taking slices through a response surface and gives a useful view of the data. Chapter 11 is a short discussion about manipulating a lattice object – the plotting functions create a lattice object that is printed if it is not saved to an object. Chapter 12 is a brief look at interacting with trellis displays – in particular identifying points in the display.

Part III takes a look at extending the trellis graphics setup. Chapters 13 and 14 provide a a good introduction to writing custom panel functions to customise the type of display and the functions that are providing with the lattice library to build up a new type of display.

Overall Comment: This is a useful book for learning the lattice graphics package by examples with some discussion about the various components that make up the system. For a user who only wants to dabble with these graphics the book is probably too extensive as there are other books or freely available documents that introducing lattice graphics.