| Physical description |
xvii, 544 pages : illustrations (some color) ; 26 cm. |
| Series |
Chapman & Hall/CRC texts in statistical science series ; 120. |
|
Texts in statistical science ; 120.
|
| Notes |
"A Chapman & Hall book." |
| Bibliography |
Includes bibliographical references and index. |
| Contents |
Machine generated contents note: 1.Introduction -- 1.1.Data visualization and categorical data: Overview -- 1.2.What is categorical data? -- 1.2.1.Case form vs. frequency form -- 1.2.2.Frequency data vs. count data -- 1.2.3.Univariate, bivariate, and multivariate data -- 1.2.4.Explanatory vs. response variables -- 1.3.Strategies for categorical data analysis -- 1.3.1.Hypothesis testing approaches -- 1.3.2.Model building approaches -- 1.4.Graphical methods for categorical data -- 1.4.1.Goals and design principles for visual data display -- 1.4.2.Categorical data require different graphical methods -- 1.4.3.Effect ordering and rendering for data display -- 1.4.4.Interactive and dynamic graphics -- 1.4.5.Visualization = Graphing + Fitting + Graphing -- 1.4.6.Data plots, model plots, and data+model plots -- 1.4.7.The 80-20 rule -- 1.5.Chapter summary -- 1.6.Lab exercises -- 2.Working with Categorical Data -- 2.1.Working with R data: vectors, matrices, arrays, and data frames -- |
|
Contents note continued: 2.1.1.Vectors -- 2.1.2.Matrices -- 2.1.3.Arrays -- 2.1.4.Data frames -- 2.2.Forms of categorical data: case form, frequency form, and table form -- 2.2.1.Case form -- 2.2.2.Frequency form -- 2.2.3.Table form -- 2.3.Ordered factors and reordered tables -- 2.4.Generating tables: table and xtabs -- 2.4.1.table() -- 2.4.2.xtabs() -- 2.5.Printing tables: structable and ftable -- 2.5.1.Text output -- 2.6.Subsetting data -- 2.6.1.Subsetting tables -- 2.6.2.Subsetting structables -- 2.6.3.Subsetting data frames -- 2.7.Collapsing tables -- 2.7.1.Collapsing over table factors -- 2.7.2.Collapsing table levels -- 2.8.Converting among frequency tables and data frames -- 2.8.1.Table form to frequency form -- 2.8.2.Case form to table form -- 2.8.3.Table form to case form -- 2.8.4.Publishing tables to LATEX or HTML -- 2.9.A complex example: TV viewing data* -- 2.9.1.Creating data frames and arrays -- 2.9.2.Subsetting and collapsing -- 2.10.Lab exercises -- |
|
Contents note continued: 3.Fitting and Graphing Discrete Distributions -- 3.1.Introduction to discrete distributions -- 3.1.1.Binomial data -- 3.1.2.Poisson data -- 3.1.3.Type-token distributions -- 3.2.Characteristics of discrete distributions -- 3.2.1.The binomial distribution -- 3.2.2.The Poisson distribution -- 3.2.3.The negative binomial distribution -- 3.2.4.The geometric distribution -- 3.2.5.The logarithmic series distribution -- 3.2.6.Power series family -- 3.3.Fitting discrete distributions -- 3.3.1.R tools for discrete distributions -- 3.3.2.Plots of observed and fitted frequencies -- 3.4.Diagnosing discrete distributions: Ord plots -- 3.5.Poissonness plots and generalized distribution plots -- 3.5.1.Features of the Poissonness plot -- 3.5.2.Plot construction -- 3.5.3.The distplot function -- 3.5.4.Plots for other distributions -- 3.6.Fitting discrete distributions as generalized linear models* -- 3.6.1.Covariates, overdispersion, and excess zeros -- |
|
Contents note continued: 3.7.Chapter summary -- 3.8.Lab exercises -- 4.Two-Way Contingency Tables -- 4.1.Introduction -- 4.2.Tests of association for two-way tables -- 4.2.1.Notation and terminology -- 4.2.2.2 by 2 tables: Odds and odds ratios -- 4.2.3.Larger tables: Overall analysis -- 4.2.4.Tests for ordinal variables -- 4.2.5.Sample CMH profiles -- 4.3.Stratified analysis -- 4.3.1.Computing strata-wise statistics -- 4.3.2.Assessing homogeneity of association -- 4.4.Fourfold display for 2 x 2 tables -- 4.4.1.Confidence rings for odds ratio -- 4.4.2.Stratified analysis for 2 x 2 x k tables -- 4.5.Sieve diagrams -- 4.5.1.Two-way tables -- 4.5.2.Larger tables: The strucplot framework -- 4.6.Association plots -- 4.7.Observer agreement -- 4.7.1.Measuring agreement -- 4.7.2.Observer agreement chart -- 4.7.3.Observer bias in agreement -- 4.8.Trilinear plots -- 4.9.Chapter summary -- 4.10.Lab exercises -- 5.Mosaic Displays for n-Way Tables -- 5.1.Introduction -- 5.2.Two-way tables -- |
|
Contents note continued: 5.2.1.Shading levels -- 5.2.2.Interpretation and reordering -- 5.3.The strucplot framework -- 5.3.1.Components overview -- 5.3.2.Shading schemes -- 5.4.Three-way and larger tables -- 5.4.1.A primer on loglinear models -- 5.4.2.Fitting models -- 5.5.Model and plot collections -- 5.5.1.Sequential plots and models -- 5.5.2.Causal models -- 5.5.3.Partial association -- 5.6.Mosaic matrices for categorical data -- 5.6.1.Mosaic matrices for pairwise associations -- 5.6.2.Generalized mosaic matrices and pairs plots -- 5.7.3D mosaics -- 5.8.Visualizing the structure of loglinear models -- 5.8.1.Mutual independence -- 5.8.2.Joint independence -- 5.9.Related visualization methods -- 5.9.1.Doubledecker plots -- 5.9.2.Generalized odds ratios* -- 5.10.Chapter summary -- 5.11.Lab exercises -- 6.Correspondence Analysis -- 6.1.Introduction -- 6.2.Simple correspondence analysis -- 6.2.1.Notation and terminology -- 6.2.2.Geometric and statistical properties -- |
|
Contents note continued: 6.2.3.R software for correspondence analysis -- 6.2.4.Correspondence analysis and mosaic displays -- 6.3.Multi-way tables: Stacking and other tricks -- 6.3.1.Interactive coding in R -- 6.3.2.Marginal tables and supplementary variables -- 6.4.Multiple correspondence analysis -- 6.4.1.Bivariate MCA -- 6.4.2.The Burt matrix -- 6.4.3.Multivariate MCA -- 6.5.Biplots for contingency tables -- 6.5.1.CA bilinear biplots -- 6.5.2.Biadditive biplots -- 6.6.Chapter summary -- 6.7.Lab exercises -- 7.Logistic Regression Models -- 7.1.Introduction -- 7.2.The logistic regression model -- 7.2.1.Fitting a logistic regression model -- 7.2.2.Model tests for simple logistic regression -- 7.2.3.Plotting a binary response -- 7.2.4.Grouped binomial data -- 7.3.Multiple logistic regression models -- 7.3.1.Conditional plots -- 7.3.2.Full-model plots -- 7.3.3.Effect plots -- 7.4.Case studies -- 7.4.1.Simple models: Group comparisons and effect plots -- |
|
Contents note continued: 7.4.2.More complex models: Model selection and visualization -- 7.5.Influence and diagnostic plots -- 7.5.1.Residuals and leverage -- 7.5.2.Influence diagnostics -- 7.5.3.Other diagnostic plots* -- 7.6.Chapter summary -- 7.7.Lab exercises -- 8.Models for Polytomous Responses -- 8.1.Ordinal response -- 8.1.1.Latent variable interpretation -- 8.1.2.Fitting the proportional odds model -- 8.1.3.Testing the proportional odds assumption -- 8.1.4.Graphical assessment of proportional odds -- 8.1.5.Visualizing results for the proportional odds model -- 8.2.Nested dichotomies -- 8.3.Generalized logit model -- 8.4.Chapter summary -- 8.5.Lab exercises -- 9.Loglinear and LogIt Models for Contingency Tables -- 9.1.Introduction -- 9.2.Loglinear models for frequencies -- 9.2.1.Loglinear models as ANOVA models for frequencies -- 9.2.2.Loglinear models for three-way tables -- 9.2.3.Loglinear models as GLMs for frequencies -- 9.3.Fitting and testing loglinear models -- |
|
Contents note continued: 9.3.1.Model fitting functions -- 9.3.2.Goodness-of-fit tests -- 9.3.3.Residuals for loglinear models -- 9.3.4.Using loglm() -- 9.3.5.Using glm() -- 9.4.Equivalent logit models -- 9.5.Zero frequencies -- 9.6.Chapter summary -- 9.7.Lab exercises -- 10.Extending Loglinear Models -- 10.1.Models for ordinal variables -- 10.1.1.Loglinear models for ordinal variables -- 10.1.2.Visualizing model structure -- 10.1.3.Log-multiplicative (RC) models -- 10.2.Square tables -- 10.2.1.Quasi-independence, symmetry, quasi-symmetry, and topological models -- 10.2.2.Ordinal square tables -- 10.3.Three-way and higher-dimensional tables -- 10.4.Multivariate responses* -- 10.4.1.Bivariate, binary response models -- 10.4.2.More complex models -- 10.5.Chapter summary -- 10.6.Lab exercises -- 11.Generalized Linear Models for Count Data -- 11.1.Components of generalized linear models -- 11.1.1.Variance functions -- 11.1.2.Hypothesis tests for coefficients -- |
|
Contents note continued: 11.1.3.Goodness-of-fit tests -- 11.1.4.Comparing non-nested models -- 11.2.GLMs for count data -- 11.3.Models for overdispersed count data -- 11.3.1.The quasi-Poisson model -- 11.3.2.The negative-binomial model -- 11.3.3.Visualizing the mean[-]variance relation -- 11.3.4.Testing overdispersion -- 11.3.5.Visualizing goodness-of-fit -- 11.4.Models for excess zero counts -- 11.4.1.Zero-inflated models -- 11.4.2.Hurdle models -- 11.4.3.Visualizing zero counts -- 11.5.Case studies -- 11.5.1.Cod parasites -- 11.5.2.Demand for medical care by the elderly -- 11.6.Diagnostic plots for model checking -- 11.6.1.Diagnostic measures and residuals for GLMs -- 11.6.2.Quantile[-]quantile and half-normal plots -- 11.7.Multivariate response GLM models* -- 11.7.1.Analyzing correlations: HE plots -- 11.7.2.Analyzing associations: Odds ratios and fourfold plots -- 11.8.Chapter summary -- 11.9.Lab exercises. |
| Other author |
Meyer, David, 1973-
|
| Subject |
Mathematics -- Data processing.
|
|
R (Computer program language)
|
| ISBN |
9781498725835 |
|
149872583X |
|
