Machine generated contents note: 1.Introduction -- 1.1.Samples versus Populations -- 1.2.Software -- 1.3.R Basics -- 1.3.1.Entering Data -- 1.3.2.R Functions and Packages -- 1.3.3.Data Sets -- 1.3.4.Arithmetic Operations -- 2.Numerical And Graphical Summaries Of Data -- 2.1.Basic Summation Notation -- 2.2.Measures of Location -- 2.2.1.The Sample Mean -- 2.2.2.R Function Mean -- 2.2.3.The Sample Median -- 2.2.4.R Function for the Median -- 2.2.5.A Criticism of the Median: It Might Trim Too Many Values -- 2.2.6.R Function for the Trimmed Mean -- 2.2.7.A Winsorized Mean -- 2.2.8.R Function winmean -- 2.2.9.What Is a Measure of Location? -- 2.3.Measures of Variation or Scale -- 2.3.1.Sample Variance and Standard Deviation -- 2.3.2.R Functions for the Variance and Standard Deviation -- 2.3.3.The Interquartile Range -- 2.3.4.R Function idealf -- 2.3.5.Winsorized Variance -- 2.3.6.R Function winvar -- 2.3.7.Median Absolute Deviation -- 2.3.8.R Function mad --

Contents note continued: 2.3.9.Average Absolute Distance from the Median -- 2.3.10.Other Robust Measures of Variation -- 2.3.11.R Functions bivar, pbvar, tauvar, and tbs -- 2.4.Detecting Outliers -- 2.4.1.A Method Based on the Mean and Variance -- 2.4.2.A Better Outlier Detection Rule: The MAD-Median Rule -- 2.4.3.R Function out -- 2.4.4.The Boxplot -- 2.4.5.R Function boxplot -- 2.4.6.Modifications of the Boxplot Rule for Detecting Outliers -- 2.4.7.R Function outbox -- 2.4.8.Other Measures of Location -- 2.4.9.R Functions mom and onestep -- 2.5.Histograms -- 2.5.1.R Functions hist and splot -- 2.6.Kernel Density Estimators -- 2.6.1.R Functions kdplot and akerd -- 2.7.Stem-and-Leaf Displays -- 2.7.1.R Function stem -- 2.8.Skewness -- 2.8.1.Transforming Data -- 2.9.Choosing a Measure of Location -- 2.10.Covariance and Pearson's Correlation -- 2.11.Exercises -- 3.Probability And Related Concepts -- 3.1.Basic Probability -- 3.2.Expected Values --

Contents note continued: 3.3.Conditional Probability and Independence -- 3.4.Population Variance -- 3.5.The Binomial Probability Function -- 3.6.Continuous Variables and the Normal Curve -- 3.6.1.Computing Probabilities Associated with Normal Distributions -- 3.6.2.R Function pnorm -- 3.7.Understanding the Effects of Non-Normality -- 3.7.1.Skewness -- 3.8.Pearson's Correlation and the Population Covariance -- 3.8.1.Computing the Population Covariance and Pearson's Correlation -- 3.9.Some Rules about Expected Values -- 3.10.Chi-Squared Distributions -- 3.11.Exercises -- 4.Sampling Distributions And Confidence Intervals -- 4.1.Random Sampling -- 4.2.Sampling Distributions -- 4.2.1.Sampling Distribution of the Sample Mean -- 4.2.2.Computing Probabilities Associated with the Sample Mean -- 4.3.A Confidence Interval for the Population Mean -- 4.3.1.Known Variance -- 4.3.2.Confidence Intervals When σ Is Not Known -- 4.3.3.R Functions pt and qt --

Contents note continued: 4.3.4.Confidence Interval for the Population Mean Using Student's T -- 4.3.5.R Function t.test -- 4.4.Judging Location Estimators Based on Their Sampling Distribution -- 4.4.1.Trimming and Accuracy: Another Perspective -- 4.5.An Approach to Non-Normality: The Central Limit Theorem -- 4.6.Student's T and Non-Normality -- 4.7.Confidence Intervals for the Trimmed Mean -- 4.7.1.Estimating the Standard Error of a Trimmed Mean -- 4.7.2.R Function trimse -- 4.8.A Confidence Interval for the Population Trimmed Mean -- 4.8.1.R Function trimci -- 4.9.Transforming Data -- 4.10.Confidence Interval for the Population Median -- 4.10.1.R Function sint -- 4.10.2.Estimating the Standard Error of the Sample Median -- 4.10.3.R Function msmedse -- 4.10.4.More Concerns about Tied Values -- 4.11.A Remark About MOM and M-Estimators -- 4.12.Confidence Intervals for the Probability of Success -- 4.12.1.R Functions binomci and acbinomci -- 4.13.Exercises -- 5.Hypothesis Testing --

Contents note continued: 5.1.The Basics of Hypothesis Testing -- 5.1.1.P-Value or Significance Level -- 5.1.2.R Function t.test -- 5.1.3.Criticisms of Two-Sided Hypothesis Testing and P-Values -- 5.1.4.Summary and Generalization -- 5.2.Power and Type II Errors -- 5.2.1.Understanding How n, α, and σ Are Related to Power -- 5.3.Testing Hypotheses about the Mean When σ Is Not Known -- 5.4.Controlling Power and Determining n -- 5.4.1.Choosing n Prior to Collecting Data -- 5.4.2.R Function power.t.test -- 5.4.3.Stein's Method: Judging the Sample Size When Data Are Available -- 5.4.4.R Functions stein1 and stein2 -- 5.5.Practical Problems with Student's T Test -- 5.6.Hypothesis Testing Based on a Trimmed Mean -- 5.6.1.R Function trimci -- 5.6.2.R Functions stein1.tr and stein2.tr -- 5.7.Testing Hypotheses about the Population Median -- 5.7.1.R Function sintv2 -- 5.8.Making Decisions about Which Measure of Location to Use -- 5.9.Exercises --

Contents note continued: 6.Regression And Correlation -- 6.1.The Least Squares Principle -- 6.2.Confidence Intervals and Hypothesis Testing -- 6.2.1.Classic Inferential Techniques -- 6.2.2.Multiple Regression -- 6.2.3.R Functions ols, lm, and olsplot -- 6.3.Standardized Regression -- 6.4.Practical Concerns about Least Squares Regression and How They Might Be Addressed -- 6.4.1.The Effect of Outliers on Least Squares Regression -- 6.4.2.Beware of Bad Leverage Points -- 6.4.3.Beware of Discarding Outliers among the Y Values -- 6.4.4.Do Not Assume Homoscedasticity or That the Regression Line Is Straight -- 6.4.5.Violating Assumptions When Testing Hypotheses -- 6.4.6.Dealing with Heteroscedasticity: The HC4 Method -- 6.4.7.R Functions olshc4 and hc4test -- 6.5.Pearson's Correlation and the Coefficient of Determination -- 6.5.1.A Closer Look at Interpreting r -- 6.6.Testing H0: ρ = 0 -- 6.6.1.R Functions cor.test and pwr.t.test -- 6.6.2.R Function pwr.r.test --

Contents note continued: 6.6.3.Testing H0: ρ = 0 When There is Heteroscedasticity -- 6.6.4.R Function pcorhc4 -- 6.6.5.When Is It Safe to Conclude That Two Variables Are Independent? -- 6.7.A Regression Method for Estimating the Median of Y and Other Quantiles -- 6.7.1.R Function rqfit -- 6.8.Detecting Heteroscedasticity -- 6.8.1.R Function khomreg -- 6.9.Concluding Remarks -- 6.10.Exercises -- 7.Bootstrap Methods -- 7.1.Bootstrap-t Method -- 7.1.1.Symmetric Confidence Intervals -- 7.1.2.Exact Nonparametric Confidence Intervals for Means Are Impossible -- 7.2.The Percentile Bootstrap Method -- 7.3.Inferences about Robust Measures of Location -- 7.3.1.Using the Percentile Method -- 7.3.2.R Functions onesampb, momci, and trimpb -- 7.3.3.The Bootstrap-t Method Based on Trimmed Means -- 7.3.4.R Function trimcibt -- 7.4.Estimating Power When Testing Hypotheses about a Trimmed Mean -- 7.4.1.R Functions powt1est and powt1an -- 7.5.A Bootstrap Estimate of Standard Errors --

Contents note continued: 7.5.1.R Function bootse -- 7.6.Inferences about Pearson's Correlation: Dealing with Heteroscedasticity -- 7.6.1.R Function pcorb -- 7.7.Bootstrap Methods for Least Squares Regression -- 7.7.1.R Functions hc4wtest, olswbtest, lsfitci -- 7.8.Detecting Associations Even When There Is Curvature -- 7.8.1.R Functions indt and medind -- 7.9.Quantile Regression -- 7.9.1.R Functions qregci and rqtest -- 7.9.2.A Test for Homoscedasticity Using a Quantile Regression Approach -- 7.9.3.R Function qhomt -- 7.10.Regression: Which Predictors Are Best? -- 7.10.1.R Function regpre -- 7.10.2.Least Angle Regression -- 7.10.3.R Function larsR -- 7.11.Comparing Correlations -- 7.11.1.R Functions TWOpov and TWOpNOV -- 7.12.Empirical Likelihood -- 7.13.Exercises -- 8.Comparing Two Independent Groups -- 8.1.Student's T Test -- 8.1.1.Choosing the Sample Sizes -- 8.1.2.R Function power.t.test -- 8.2.Relative Merits of Student's T -- 8.3.Welch's Heteroscedastic Method for Means --

Contents note continued: 8.3.1.R Function t.test -- 8.3.2.Tukey's Three-Decision Rule -- 8.3.3.Non-Normality and Welch's Method -- 8.3.4.Three Modern Insights Regarding Methods for Comparing Means -- 8.4.Methods for Comparing Medians and Trimmed Means -- 8.4.1.Yuen's Method for Trimmed Means -- 8.4.2.R Functions yuen and fac2list -- 8.4.3.Comparing Medians -- 8.4.4.R Function msmed -- 8.5.Percentile Bootstrap Methods for Comparing Measures of Location -- 8.5.1.Using Other Measures of Location -- 8.5.2.Comparing Medians -- 8.5.3.R Function medpb2 -- 8.5.4.Some Guidelines on When to Use the Percentile Bootstrap Method -- 8.5.5.R Functions trimpb2 and pb2gen -- 8.6.Bootstrap-t Methods for Comparing Measures of Location -- 8.6.1.Comparing Means -- 8.6.2.Bootstrap-t Method When Comparing Trimmed Means -- 8.6.3.R Functions yuenbt and yhbt -- 8.6.4.Estimating Power and Judging the Sample Sizes -- 8.6.5.R Functions powest and pow2an -- 8.7.Permutation Tests -- 8.7.1.R Function permg --

Contents note continued: 8.8.Rank-Based and Nonparametric Methods -- 8.8.1.Wilcoxon---Mann---Whitney Test -- 8.8.2.R Functions wmw and wilcox.test -- 8.8.3.Handling Tied Values and Heteroscedasticity -- 8.8.4.Cliff's Method -- 8.8.5.R functions cid and cidv2 -- 8.8.6.The Brunner---Munzel Method -- 8.8.7.R function bmp -- 8.8.8.The Kolmogorov---Smirnov Test -- 8.8.9.R Function ks -- 8.8.10.Comparing All Quantiles Simultaneously: An Extension of the Kolmogorov---Smirnov Test -- 8.8.11.R Function sband -- 8.9.Graphical Methods for Comparing Groups -- 8.9.1.Error Bars -- 8.9.2.R Function ebarplot -- 8.9.3.Plotting the Shift Function -- 8.9.4.Plotting the Distributions -- 8.9.5.R Function sumplot2g -- 8.9.6.Other Approaches -- 8.10.Comparing Measures of Scale -- 8.11.Methods for Comparing Measures of Variation -- 8.11.1.R Function comvar2 -- 8.11.2.Brown---Forsythe Method -- 8.11.3.Comparing Robust Measures of Variation -- 8.12.Measuring Effect Size --

Contents note continued: 8.12.1.R Functions yuenv2 and akp.effect -- 8.13.Comparing Correlations and Regression Slopes -- 8.13.1.R Functions twopcor, twolsreg, and tworegwb -- 8.14.Comparing Two Binomials -- 8.14.1.Storer---Kim Method -- 8.14.2.Beal's Method -- 8.14.3.R Functions twobinom, twobici, and power.prop.test -- 8.15.Making Decisions about Which Method to Use -- 8.16.Exercises -- 9.Comparing Two Dependent Groups -- 9.1.The Paired T Test -- 9.1.1.When Does the Paired T Test Perform Well? -- 9.1.2.R Function t.test -- 9.2.Comparing Robust Measures of Location -- 9.2.1.R Functions yuend, ydbt, and dmedpb -- 9.2.2.Comparing Marginal M-Estimators -- 9.2.3.R Function rmmest -- 9.3.Handling Missing Values -- 9.3.1.R Functions rm2miss and rmmismcp -- 9.4.A Different Perspective When Using Robust Measures of Location -- 9.4.1.R Functions loc2dif and 12drmci -- 9.5.The Sign Test -- 9.5.1.R Function signt -- 9.6.Wilcoxon Signed Rank Test -- 9.6.1.R Function wilcox.test --

Contents note continued: 9.7.Comparing Variances -- 9.8.Comparing Robust Measures of Scale -- 9.8.1.R Function rmrvar -- 9.9.Comparing All Quantiles -- 9.9.1.R Function lband -- 9.10.Plots for Dependent Groups -- 9.10.1.R Function g2plotdifxy -- 9.11.Exercises -- 10.One-Way Anova -- 10.1.Analysis of Variance for Independent Groups -- 10.1.1.A Conceptual Overview -- 10.1.2.ANOVA via Least Squares Regression and Dummy Coding -- 10.1.3.R Functions anova, anoval, aov, and fac2list -- 10.1.4.Controlling Power and Choosing the Sample Sizes -- 10.1.5.R Functions power.anova.test and anova.power -- 10.2.Dealing with Unequal Variances -- 10.2.1.Welch's Test -- 10.3.Judging Sample Sizes and Controlling Power When Data Are Available -- 10.3.1.R Functions bdanoval and bdanova2 -- 10.4.Trimmed Means -- 10.4.1.R Functions t1way, t1wayv2, and t1wayF -- 10.4.2.Comparing Groups Based on Medians -- 10.4.3.R Function med1way -- 10.5.Bootstrap Methods -- 10.5.1.A Bootstrap-t Method --

Contents note continued: 10.5.2.R Function t1waybt -- 10.5.3.Two Percentile Bootstrap Methods -- 10.5.4.R Functions b1way and pbadepth -- 10.5.5.Choosing a Method -- 10.6.Random Effects Model -- 10.6.1.A Measure of Effect Size -- 10.6.2.A Heteroscedastic Method -- 10.6.3.A Method Based on Trimmed Means -- 10.6.4.R Function rananova -- 10.7.Rank-Based Methods -- 10.7.1.The Kruskall---Wallis Test -- 10.8.R Function kruskal.test -- 10.8.1.Method BDM -- 10.8.2.R Function bdm -- 10.9.Exercises -- 11.Two-Way And Three-Way Designs -- 11.1.Basics of a Two-Way ANOVA Design -- 11.1.1.Interactions -- 11.1.2.R Functions interaction.plot and interplot -- 11.1.3.Interactions When There Are More than Two Levels -- 11.2.Testing Hypotheses about Main Effects and Interactions -- 11.2.1.R Function anova -- 11.2.2.Inferences about Disordinal Interactions -- 11.2.3.The Two-Way ANOVA Model -- 11.3.Heteroscedastic Methods for Trimmed Means, Including Means -- 11.3.1.R Function t2way --

Contents note continued: 11.4.Bootstrap Methods -- 11.4.1.R Functions pbad2way and t2waybt -- 11.5.Testing Hypotheses Based on Medians -- 11.5.1.R Function m2way -- 11.6.A Rank-Based Method for a Two-Way Design -- 11.6.1.R Function bdm2way -- 11.6.2.The Patel---Hoel Approach to Interactions -- 11.7.Three-Way ANOVA -- 11.7.1.R Functions anova and t3way -- 11.8.Exercises -- 12.Comparing More Than Two Dependent Groups -- 12.1.Comparing Means in a One-Way Design -- 12.1.1.R Function aov -- 12.2.Comparing Trimmed Means When Dealing with a One-Way Design -- 12.2.1.R Functions rmanova and rmdat2mat -- 12.2.2.A Bootstrap-t Method for Trimmed Means -- 12.2.3.R Function rmanovab -- 12.3.Percentile Bootstrap Methods for a One-Way Design -- 12.3.1.Method Based on Marginal Measures of Location -- 12.3.2.R Function bd1way -- 12.3.3.Inferences Based on Difference Scores -- 12.3.4.R Function rmdzero -- 12.4.Rank-Based Methods for a One-Way Design -- 12.4.1.Friedman's Test --

Contents note continued: 12.4.2.R Function friedman.test -- 12.4.3.Method BPRM -- 12.4.4.R Function bprm -- 12.5.Comments on Which Method to Use -- 12.6.Between-by-Within Designs -- 12.6.1.Method for Trimmed Means -- 12.6.2.R Function bwtrim and bw2list -- 12.6.3.A Bootstrap-t Method -- 12.6.4.R Function tsplitbt -- 12.6.5.Inferences Based on M-estimators and Other Robust Measures of Location -- 12.6.6.R Functions sppba, sppbb, and sppbi -- 12.6.7.A Rank-Based Test -- 12.6.8.R Function bwrank -- 12.7.Within-by-Within Design -- 12.7.1.R Function wwtrim -- 12.8.Three-Way Designs -- 12.8.1.R Functions bbwtrim, bwwtrim, and wwwtrim -- 12.8.2.Data Management: R Functions bw2list and bbw2list -- 12.9.Exercises -- 13.Multiple Comparisons -- 13.1.One-Way ANOVA, Independent Groups -- 13.1.1.Fisher's Least Significant Difference Method -- 13.1.2.The Tukey---Kramer Method -- 13.1.3.R Function TukeyHSD -- 13.1.4.Tukey---Kramer and the ANOVA F Test -- 13.1.5.A Step-Down Method --

Contents note continued: 13.1.6.Dunnett's T3 -- 13.1.7.Games---Howell Method -- 13.1.8.Comparing Trimmed Means -- 13.1.9.R Function lincon -- 13.1.10.Alternative Methods for Controlling FWE -- 13.1.11.Percentile Bootstrap Methods for Comparing Trimmed Means, Medians, and M-estimators -- 13.1.12.R Functions medpb, tmcppb, pbmcp, and mcppb20 -- 13.1.13.A Bootstrap-t Method -- 13.1.14.R Function linconb -- 13.1.15.Rank-Based Methods -- 13.1.16.R Functions cidmul, cidmulv2, and bmpmul -- 13.2.Two-Way, between-by-between Design -- 13.2.1.Scheffe's Homoscedastic Method -- 13.2.2.Heteroscedastic Methods -- 13.2.3.Extension of Welch---Sidak and Kaiser---Bowden Methods to Trimmed Means -- 13.2.4.R Function kbcon -- 13.2.5.R Function con2way -- 13.2.6.Linear Contrasts Based on Medians -- 13.2.7.R Functions msmed and mcp2med -- 13.2.8.Bootstrap Methods -- 13.2.9.R Functions linconb, mcp2a, and bbmcppb -- 13.2.10.The Patel---Hoel Rank-Based Interaction Method -- 13.2.11.R Function rimul --

Contents note continued: 13.3.Judging Sample Sizes -- 13.3.1.Tamhane's Procedure -- 13.3.2.R Function tamhane -- 13.3.3.Hochberg's Procedure -- 13.3.4.R Function hochberg -- 13.4.Methods for Dependent Groups -- 13.4.1.Linear Contrasts Based on Trimmed Means -- 13.4.2.R Function rmmcp -- 13.4.3.Comparing M-estimators -- 13.4.4.R Functions rmmcppb, dmedpb, and dtrimpb -- 13.4.5.Bootstrap-t Method -- 13.4.6.R Function bptd -- 13.5.Between-by-within Designs -- 13.5.1.R Functions bwmcp, bwamcp, bwbmcp, bwimcp, spmcpa, spmcpb, spmcpi, and bwmcppb -- 13.6.Within-by-within Designs -- 13.6.1.Three-Way Designs -- 13.6.2.R Functions con3way, mcp3atm, and rm3mcp -- 13.6.3.Bootstrap Methods for Three-Way Designs -- 13.6.4.R Functions bbwmcp, bwwmcp, bbbmcppb, bbwmcppb, bwwmcppb, and wwwmcppb -- 13.7.Exercises -- 14.Some Multivariate Methods -- 14.1.Location, Scatter, and Detecting Outliers -- 14.1.1.Detecting Outliers via Robust Measures of Location and Scatter --

Contents note continued: 14.1.2.R Functions cov.mve and com.mcd -- 14.1.3.More Measures of Location and Covariance -- 14.1.4.R Functions rmba, tbs, and ogk -- 14.1.5.R Function out -- 14.1.6.A Projection-Type Outlier Detection Method -- 14.1.7.R Functions outpro, outproMC, outproad, outproadMC, and out3d -- 14.1.8.Skipped Estimators of Location -- 14.1.9.R Functions smean -- 14.2.One-Sample Hypothesis Testing -- 14.2.1.Comparing Dependent Groups -- 14.2.2.R Functions smeancrv2, hotel1, and rmdzeroOP -- 14.3.Two-Sample Case -- 14.3.1.R Functions smean2, mat2grp, and matsplit -- 14.4.MANOVA -- 14.4.1.R Function manova -- 14.4.2.Robust MANOVA Based on Trimmed Means -- 14.4.3.R Functions MULtr.anova and MULAOVp -- 14.4.4.A Multivariate Extension of the Wilcoxon---Mann---Whitney Test -- 14.4.5.Explanatory Measure of Effect Size: A Projection-Type Generalization -- 14.4.6.R Function mulwmwv2 -- 14.5.Rank-Based Multivariate Methods -- 14.5.1.The Munzel---Brunner Method --

Contents note continued: 14.5.2.R Function mulrank -- 14.5.3.The Choi---Marden Multivariate Rank Test -- 14.5.4.R Function cmanova -- 14.6.Multivariate Regression -- 14.6.1.Multivariate Regression Using R -- 14.6.2.Robust Multivariate Regression -- 14.6.3.R Function mlrreg and mopreg -- 14.7.Principal Components -- 14.7.1.R Functions prcomp and regpca -- 14.7.2.Robust Principal Components -- 14.7.3.R Functions outpca, robpca, robpcaS, Ppca, and Ppca.summary -- 14.8.Exercises -- 15.Robust Regression And Measures Of Association -- 15.1.Robust Regression Estimators -- 15.1.1.The Theil---Sen Estimator -- 15.1.2.R Functions tsreg and regplot -- 15.1.3.Least Median of Squares -- 15.1.4.Least Trimmed Squares and Least Trimmed Absolute Value Estimators -- 15.1.5.R Functions lmsreg, ltsreg, and ltareg -- 15.1.6.M-Estimators -- 15.1.7.R Function chreg -- 15.1.8.Deepest Regression Line -- 15.1.9.R Function mdepreg -- 15.1.10.Skipped Estimators -- 15.1.11.R Functions opreg and opregMC --

Contents note continued: 15.1.12.S-estimators and an E-Type Estimator -- 15.1.13.R Function tsts -- 15.2.Comments on Choosing a Regression Estimator -- 15.3.Testing Hypotheses When Using Robust Regression Estimators -- 15.3.1.R Functions regtest, regtestMC, regci, and regciMC -- 15.3.2.Comparing Measures of Location via Dummy Coding -- 15.4.Dealing with Curvature: Smoothers -- 15.4.1.Cleveland's Smoother -- 15.4.2.R Functions lowess and lplot -- 15.4.3.Smoothers Based on Robust Measures of Location -- 15.4.4.R Functions rplot and rplotsm -- 15.4.5.More Smoothers -- 15.4.6.R Functions kerreg, runpd, and qsmcobs -- 15.4.7.Prediction When X Is Discrete: The R Function rundis -- 15.4.8.Seeing Curvature with More than Two Predictors -- 15.4.9.R Function prplot -- 15.4.10.Some Alternative Methods -- 15.5.Some Robust Correlations and Tests of Independence -- 15.5.1.Kendall's tau -- 15.5.2.Spearman's rho -- 15.5.3.Winsorized Correlation -- 15.5.4.R Function wincor --

Contents note continued: 15.5.5.OP Correlation -- 15.5.6.R Function scor -- 15.5.7.Inferences about Robust Correlations: Dealing with Heteroscedasticity -- 15.5.8.R Function corb -- 15.6.Measuring the Strength of an Association Based on a Robust Fit -- 15.7.Comparing the Slopes of Two Independent Groups -- 15.7.1.R Functions reg2ci, runmean2g, and l2plot -- 15.8.Tests for Linearity -- 15.8.1.R Functions lintest, lintestMC, and linchk -- 15.9.Identifying the Best Predictors -- 15.9.1.R Functions regpord, ts2str, and sm2strv7 -- 15.10.Detecting Interactions and Moderator Analysis -- 15.10.1.R Functions adtest -- 15.10.2.Graphical Methods for Assessing Interactions -- 15.10.3.R Functions kercon, runsm2g, regi, ols.plot.inter, and reg.plot.inter -- 15.11.ANCOVA -- 15.11.1.Classic ANCOVA -- 15.11.2.Some Modern ANCOVA Methods -- 15.11.3.R Functions ancsm, Qancsm, ancova, ancpb, ancbbpb, and ancboot -- 15.12.Exercises -- 16.Basic Methods For Analyzing Categorical Data --

Contents note continued: 16.1.Goodness of Fit -- 16.1.1.R Functions chisq.test and pwr.chisq.test -- 16.2.A Test of Independence -- 16.2.1.R Function chi.test.ind -- 16.3.Detecting Differences in the Marginal Probabilities -- 6.3.1.R Functions contab and mcnemar.test -- 16.4.Measures of Association -- 16.4.1.The Proportion of Agreement -- 16.4.2.Kappa -- 16.4.3.Weighted Kappa -- 16.4.4.R Function Ckappa -- 16.5.Logistic Regression -- 16.5.1.R Functions glm and logreg -- 16.5.2.A Confidence Interval for the Odds Ratio -- 16.5.3.R Function ODDSR.CI -- 16.5.4.Smoothers for Logistic Regression -- 16.5.5.R Functions logrsm, rplot.bin, and logSM -- 16.6.Exercises.