Data Analysis and Graphics Using R: An Example-based ApproachModern statistical software systems provide sophisticated tools for researchers who need to manipulate and display their data. Using such systems requires training both in the software itself and in the statistical methods that it relies on. Concentrating on the freely available R system, this book demonstrates recently implemented approaches and methods in statistical analysis. The authors introduce elementary concepts in statistics through examples of real-world data analysis drawn from the authors' experience, both as teachers and as consultants. R code and data sets for all examples are available on the Internet. This emphasis on practical methodology combined with a tutorial approach makes the book accessible to anyone with a knowledge of undergraduate statistics, whether an upper-graduate student, a researcher, or a practising scientist or statistician. The methods demonstrated are suitable for use in a wide variety of disciplines, from social sciences to medicine, engineering and science. |
Contents
A Brief Introduction to | 1 |
Styles of Data Analysis | 2 |
Additional Points on the Use of R in This Book | 23 |
1 | 29 |
2 | 42 |
1 | 50 |
Statistical Models | 52 |
3 | 59 |
Regression with a Single Predictor | 107 |
Multiple Linear Regression | 134 |
Exploiting the Linear Model Framework | 175 |
Logistic Regression and Other Generalized Linear Models | 197 |
Multilevel Models Time Series and Repeated Measures | 224 |
Treebased Classification and Regression | 259 |
Multivariate Data Exploration and Discrimination | 281 |
The R System Additional Topics | 300 |
Common terms and phrases
analysis of variance anova apply autocorrelation bodywt boxplot brainwt calculations Chapter coef coefficients column confidence interval Cook's distance correlation cross-validation curve DAAG package data frame data set default degrees of freedom deviance diagnostic plots effects Error t value Estimate Std example explanatory variables F-statistic factor female Figure fitted values formula function gives graphics Intercept lattice levels linear models log dist log(odds logistic regression Maindonald mean square median methodology methods model matrix multi-level modeling multiple NoOfSites normal distribution Note objects observations outliers output p-value panel parameter points Poisson polynomial possum predictive accuracy principal components Q-Q plot random regression model residuals rows rpart S-PLUS sample scatterplot scatterplot matrix scores specify spline split standard deviation standard error statistical structure Subsection sum of squares summary transformation treatment tree tree-based regression value Pr(>|t vapPress variance table variation vector vines weight workspace