Preface |
A Chapter by Chapter Summary |
A Brief Introduction to R / 1: |
A Short R Session / 1.1: |
R must be installed! / 1.1.1: |
Using the console (or command line) window / 1.1.2: |
Reading data from a file / 1.1.3: |
Entry of data at the command line / 1.1.4: |
Online help / 1.1.5: |
Quitting R / 1.1.6: |
The Uses of R / 1.2: |
The R Language / 1.3: |
R objects / 1.3.1: |
Retaining objects between sessions / 1.3.2: |
Vectors in R / 1.4: |
Concatenation--joining vector objects / 1.4.1: |
Subsets of vectors / 1.4.2: |
Patterned data / 1.4.3: |
Missing values / 1.4.4: |
Factors / 1.4.5: |
Data Frames / 1.5: |
Variable names / 1.5.1: |
Applying a function to the columns of a data frame / 1.5.2: |
Data frames and matrices / 1.5.3: |
Identification of rows that include missing values / 1.5.4: |
R Packages / 1.6: |
Data sets that accompany R packages / 1.6.1: |
Looping / 1.7: |
R Graphics / 1.8: |
The function plot () and allied functions / 1.8.1: |
Identification and location on the figure region / 1.8.2: |
Plotting mathematical symbols / 1.8.3: |
Row by column layouts of plots / 1.8.4: |
Graphs--additional notes / 1.8.5: |
Additional Points on the Use of R in This Book / 1.9: |
Further Reading / 1.10: |
Exercises / 1.11: |
Styles of Data Analysis / 2: |
Revealing Views of the Data / 2.1: |
Views of a single sample / 2.1.1: |
Patterns in grouped data / 2.1.2: |
Patterns in bivariate data--the scatterplot / 2.1.3: |
Multiple variables and times / 2.1.4: |
Lattice (trellis style) graphics / 2.1.5: |
What to look for in plots / 2.1.6: |
Data Summary / 2.2: |
Mean and median / 2.2.1: |
Standard deviation and inter-quartile range / 2.2.2: |
Correlation / 2.2.3: |
Statistical Analysis Strategies / 2.3: |
Helpful and unhelpful questions / 2.3.1: |
Planning the formal analysis / 2.3.2: |
Changes to the intended plan of analysis / 2.3.3: |
Recap / 2.4: |
Statistical Models / 2.5: |
Regularities / 3.1: |
Mathematical models / 3.1.1: |
Models that include a random component / 3.1.2: |
Smooth and rough / 3.1.3: |
The construction and use of models / 3.1.4: |
Model formulae / 3.1.5: |
Distributions: Models for the Random Component / 3.2: |
Discrete distributions / 3.2.1: |
Continuous distributions / 3.2.2: |
The Uses of Random Numbers / 3.3: |
Simulation / 3.3.1: |
Sampling from populations / 3.3.2: |
Model Assumptions / 3.4: |
Random sampling assumptions--independence / 3.4.1: |
Checks for normality / 3.4.2: |
Checking other model assumptions / 3.4.3: |
Are non-parametric methods the answer? / 3.4.4: |
Why models matter--adding across contingency tables / 3.4.5: |
An Introduction to Formal Inference / 3.5: |
Standard Errors / 4.1: |
Population parameters and sample statistics / 4.1.1: |
Assessing accuracy--the standard error / 4.1.2: |
Standard errors for differences of means / 4.1.3: |
The standard error of the median / 4.1.4: |
Resampling to estimate standard errors: bootstrapping / 4.1.5: |
Calculations Involving Standard Errors: the t-Distribution / 4.2: |
Confidence Intervals and Hypothesis Tests / 4.3: |
One- and two-sample intervals and tests for means / 4.3.1: |
Confidence intervals and tests for proportions / 4.3.2: |
Confidence intervals for the correlation / 4.3.3: |
Contingency Tables / 4.4: |
Rare and endangered plant species / 4.4.1: |
Additional notes / 4.4.2: |
One-Way Unstructured Comparisons / 4.5: |
Displaying means for the one-way layout / 4.5.1: |
Multiple comparisons / 4.5.2: |
Data with a two-way structure / 4.5.3: |
Presentation issues / 4.5.4: |
Response Curves / 4.6: |
Data with a Nested Variation Structure / 4.7: |
Degrees of freedom considerations / 4.7.1: |
General multi-way analysis of variance designs / 4.7.2: |
Resampling Methods for Tests and Confidence Intervals / 4.8: |
The one-sample permutation test / 4.8.1: |
The two-sample permutation test / 4.8.2: |
Bootstrap estimates of confidence intervals / 4.8.3: |
Further Comments on Formal Inference / 4.9: |
Confidence intervals versus hypothesis tests / 4.9.1: |
If there is strong prior information, use it! / 4.9.2: |
Regression with a Single Predictor / 4.10: |
Fitting a Line to Data / 5.1: |
Lawn roller example / 5.1.1: |
Calculating fitted values and residuals / 5.1.2: |
Residual plots / 5.1.3: |
The analysis of variance table / 5.1.4: |
Outliers, Influence and Robust Regression / 5.2: |
Standard Errors and Confidence Intervals / 5.3: |
Confidence intervals and tests for the slope / 5.3.1: |
SEs and confidence intervals for predicted values / 5.3.2: |
Implications for design / 5.3.3: |
Regression versus Qualitative ANOVA Comparisons / 5.4: |
Assessing Predictive Accuracy / 5.5: |
Training/test sets, and cross-validation / 5.5.1: |
Cross-validation--an example / 5.5.2: |
Bootstrapping / 5.5.3: |
A Note on Power Transformations / 5.6: |
Size and Shape Data / 5.7: |
Allometric growth / 5.7.1: |
There are two regression lines! / 5.7.2: |
The Model Matrix in Regression / 5.8: |
Methodological References / 5.9: |
Multiple Linear Regression / 5.11: |
Basic Ideas: Book Weight and Brain Weight Examples / 6.1: |
Omission of the intercept term / 6.1.1: |
Diagnostic plots / 6.1.2: |
Further investigation of influential points / 6.1.3: |
Example: brain weight / 6.1.4: |
Multiple Regression Assumptions and Diagnostics / 6.2: |
Influential outliers and Cook's distance / 6.2.1: |
Component plus residual plots / 6.2.2: |
Further types of diagnostic plot / 6.2.3: |
Robust and resistant methods / 6.2.4: |
A Strategy for Fitting Multiple Regression Models / 6.3: |
Preliminaries / 6.3.1: |
Model fitting / 6.3.2: |
An example--the Scottish hill race data / 6.3.3: |
Measures for the Comparison of Regression Models / 6.4: |
R[superscript 2] and adjusted R[superscript 2] / 6.4.1: |
AIC and related statistics / 6.4.2: |
How accurately does the equation predict? / 6.4.3: |
An external assessment of predictive accuracy / 6.4.4: |
Interpreting Regression Coefficients--the Labor Training Data / 6.5: |
Problems with Many Explanatory Variables / 6.6: |
Variable selection issues / 6.6.1: |
Principal components summaries / 6.6.2: |
Multicollinearity / 6.7: |
A contrived example / 6.7.1: |
The variance inflation factor (VIF) / 6.7.2: |
Remedying multicollinearity / 6.7.3: |
Multiple Regression Models--Additional Points / 6.8: |
Confusion between explanatory and dependent variables / 6.8.1: |
Missing explanatory variables / 6.8.2: |
The use of transformations / 6.8.3: |
Non-linear methods--an alternative to transformation? / 6.8.4: |
Exploiting the Linear Model Framework / 6.9: |
Levels of a Factor--Using Indicator Variables / 7.1: |
Example--sugar weight / 7.1.1: |
Different choices for the model matrix when there are factors / 7.1.2: |
Polynomial Regression / 7.2: |
Issues in the choice of model / 7.2.1: |
Fitting Multiple Lines / 7.3: |
Methods for Passing Smooth Curves through Data / 7.4: |
Scatterplot smoothing--regression splines / 7.4.1: |
Other smoothing methods / 7.4.2: |
Generalized additive models / 7.4.3: |
Smoothing Terms in Multiple Linear Models / 7.5: |
Logistic Regression and Other Generalized Linear Models / 7.6: |
Generalized Linear Models / 8.1: |
Transformation of the expected value on the left / 8.1.1: |
Noise terms need not be normal / 8.1.2: |
Log odds in contingency tables / 8.1.3: |
Logistic regression with a continuous explanatory variable / 8.1.4: |
Logistic Multiple Regression / 8.2: |
A plot of contributions of explanatory variables / 8.2.1: |
Cross-validation estimates of predictive accuracy / 8.2.2: |
Logistic Models for Categorical Data--an Example / 8.3: |
Poisson and Quasi-Poisson Regression / 8.4: |
Data on aberrant crypt foci / 8.4.1: |
Moth habitat example / 8.4.2: |
Residuals, and estimating the dispersion / 8.4.3: |
Ordinal Regression Models / 8.5: |
Exploratory analysis / 8.5.1: |
Proportional odds logistic regression / 8.5.2: |
Other Related Models / 8.6: |
Loglinear models / 8.6.1: |
Survival analysis / 8.6.2: |
Transformations for Count Data / 8.7: |
Multi-level Models, Time Series and Repeated Measures / 8.8: |
Introduction / 9.1: |
Example--Survey Data, with Clustering / 9.2: |
Alternative models / 9.2.1: |
Instructive, though faulty, analyses / 9.2.2: |
Predictive accuracy / 9.2.3: |
A Multi-level Experimental Design / 9.3: |
The ANOVA table / 9.3.1: |
Expected values of mean squares / 9.3.2: |
The sums of squares breakdown / 9.3.3: |
The variance components / 9.3.4: |
The mixed model analysis / 9.3.5: |
Different sources of variance--complication or focus of interest? / 9.3.6: |
Within and between Subject Effects--an Example / 9.4: |
Time Series--Some Basic Ideas / 9.5: |
Preliminary graphical explorations / 9.5.1: |
The autocorrelation function / 9.5.2: |
Autoregressive (AR) models / 9.5.3: |
Autoregressive moving average (ARMA) models--theory / 9.5.4: |
Regression Modeling with Moving Average Errors--an Example / 9.6: |
Repeated Measures in Time--Notes on the Methodology / 9.7: |
The theory of repeated measures modeling / 9.7.1: |
Correlation structure / 9.7.2: |
Different approaches to repeated measures analysis / 9.7.3: |
Further Notes on Multi-level Modeling / 9.8: |
An historical perspective on multi-level models / 9.8.1: |
Meta-analysis / 9.8.2: |
Tree-based Classification and Regression / 9.9: |
The Uses of Tree-based Methods / 10.1: |
Problems for which tree-based regression may be used / 10.1.1: |
Tree-based regression versus parametric approaches / 10.1.2: |
Summary of pluses and minuses / 10.1.3: |
Detecting Email Spam--an Example / 10.2: |
Choosing the number of splits / 10.2.1: |
Terminology and Methodology / 10.3: |
Choosing the split--regression trees / 10.3.1: |
Within and between sums of squares / 10.3.2: |
Choosing the split--classification trees / 10.3.3: |
The mechanics of tree-based regression--a trivial example / 10.3.4: |
Assessments of Predictive Accuracy / 10.4: |
Cross-validation / 10.4.1: |
The training/test set methodology / 10.4.2: |
Predicting the future / 10.4.3: |
A Strategy for Choosing the Optimal Tree / 10.5: |
Cost-complexity pruning / 10.5.1: |
Prediction error versus tree size / 10.5.2: |
Detecting Email Spam--the Optimal Tree / 10.6: |
The one-standard-deviation rule / 10.6.1: |
Interpretation and Presentation of the rpart Output / 10.7: |
Data for female heart attack patients / 10.7.1: |
Printed Information on Each Split / 10.7.2: |
Additional Notes / 10.8: |
Multivariate Data Exploration and Discrimination / 10.9: |
Multivariate Exploratory Data Analysis / 11.1: |
Scatterplot matrices / 11.1.1: |
Principal components analysis / 11.1.2: |
Discriminant Analysis / 11.2: |
Example--plant architecture / 11.2.1: |
Classical Fisherian discriminant analysis / 11.2.2: |
Logistic discriminant analysis / 11.2.3: |
An example with more than two groups / 11.2.4: |
Principal Component Scores in Regression / 11.3: |
Propensity Scores in Regression Comparisons--Labor Training Data / 11.4: |
The R System--Additional Topics / 11.5: |
Graphs in R / 12.1: |
Functions--Some Further Details / 12.2: |
Common useful functions / 12.2.1: |
User-written R functions / 12.2.2: |
Functions for working with dates / 12.2.3: |
Data input and output / 12.3: |
Input / 12.3.1: |
Data output / 12.3.2: |
Factors--Additional Comments / 12.4: |
Missing Values / 12.5: |
Lists and Data Frames / 12.6: |
Data frames as lists / 12.6.1: |
Reshaping data frames; reshape () / 12.6.2: |
Joining data frames and vectors--cbind () / 12.6.3: |
Conversion of tables and arrays into data frames / 12.6.4: |
Merging data frames--merge () / 12.6.5: |
The function sapply () and related functions / 12.6.6: |
Splitting vectors and data frames into lists--split () / 12.6.7: |
Matrices and Arrays / 12.7: |
Outer products / 12.7.1: |
Arrays / 12.7.2: |
Classes and Methods / 12.8: |
Printing and summarizing model objects / 12.8.1: |
Extracting information from model objects / 12.8.2: |
Data-bases and Environments / 12.9: |
Workspace management / 12.9.1: |
Function environments, and lazy evaluation / 12.9.2: |
Manipulation of Language Constructs / 12.10: |
Epilogue--Models / 12.11: |
S-PLUS Differences / Appendix: |
References |
Index of R Symbols and Functions |
Index of Terms |
Index of Names |