Practical statistical methods : a SAS programming approach

 Content: 1. Introduction --
 1.1. Types of Data --
 1.2. Descriptive Statistics/Data Summaries --
 1.3. Graphical and Tabular Representation --
 1.4. Population and Sample --
 1.5. Estimation and Testing Hypothesis --
 1.6. Normal Distribution --
 1.7. Nonparametric Methods --
 1.8. Some Useful Concepts --
 2. Qualitative Data --
 2.1. One Sample --
 2.1.1. Binary Data --
 2.1.2. t Categorical Responses --
 2.2. Two Independent Samples --
 2.2.1. Two Proportions --
 2.2.2. Odds Ratio and Relative Risk --
 2.2.3. Logistic Regression with One Dichotomous Explanatory Variable --
 2.2.4. Cochran-Mantel-Haenszel Test for a 2 x 2 Table --
 2.2.5. t Categorical Responses --
 2.3. Paired Two Samples --
 2.3.1. Binary Responses --
 2.3.2. t Categorical Responses --
 2.4. k Independent Samples --
 2.4.1. k Proportions --
 2.4.2. Logistic Regression When the Explanatory Variable Is Not Dichotomous 2.4.3. CMH Test --
 2.4.4. t Categorical Responses --
 2.5. Cochran's Test --
 2.6. Ordinal Data --
 2.6.1. Row Mean Score Test --
 2.6.2. Cochran-Armitage Test --
 2.6.3. Measures of Association --
 2.6.4. Ridit Analysis --
 2.6.5. Weighted Kappa --
 2.6.6. Ordinal Logistic Regression --
 2.6.6.1. Two Samples --
 2.6.6.2. k Samples --
 3. Continuous Normal Data --
 3.1. One Sample --
 3.2. Two Samples --
 3.2.1. Independent Samples --
 3.2.1.1. Means --
 3.2.1.2. Variances --
 3.2.2. Paired Samples --
 3.3. k Independent Samples --
 3.3.1. One-Way Analysis of Variance --
 3.3.1.1. Variance --
 3.3.2. Covariance Analysis --
 3.4. Multivariate Methods --
 3.4.1. Correlation, Partial, and Intraclass Correlation --
 3.4.2. Hotelling's T2 --
 3.4.2.1. One Sample --
 3.4.2.2. Two Samples --
 3.4.3. One-Way Multivariate Analysis of Variance --
 3.4.4. Profile Analysis --
 3.4.5. Discriminant Functions --
 3.4.6. Cluster Analysis --
 3.4.7. Principal Components 3.4.8. Factor Analysis --
 3.4.9. Canonical Correlation --
 3.5. Multifactor ANOVA --
 3.5.1. Crossed Factors --
 3.5.2. Tukey 1 df for Nonadditivity --
 3.5.3. Nested Factors --
 3.6. Variance Components --
 3.7. Split Plot Designs --
 3.8. Latin Square Design --
 3.9. Two-Treatment Crossover Design --
 4. Nonparametric Methods --
 4.1. One Sample --
 4.1.1. Sign Test --
 4.1.2. Wilcoxon Signed-Rank Test --
 4.1.3. Kolmogorov Goodness of Fit --
 4.1.4. Cox and Stuart Test --
 4.2. Two Samples --
 4.2.1. Wilcoxon-Mann-Whitney Test --
 4.2.2. Mood's Median Test --
 4.2.3. Kolmogorov-Smirnov --
 4.2.4. Equality of Variances --
 4.3. k Samples --
 4.3.1. Kruskal-Wallis Test --
 4.3.2. Median Test --
 4.3.3. Jonckheere Test --
 4.4. Transformations --
 4.5. Friedman Test --
 4.6. Association Measures --
 4.6.1. Spearman Rank Correlation --
 4.6.2. Kendall's Tau --
 4.6.3. Kappa Statistic --
 4.7. Censored Data 4.7.1. Kaplan-Meier Survival Distribution Function --
 4.7.2. Wilcoxon (Gehan) and Log-Rank Test --
 4.7.3. Life-Table (Acturial Method) --
 5. Regression --
 5.1. Simple Regression --
 5.2. Polynomial Regression --
 5.3. Multiple Regressions --
 5.3.1. Multicollinearity --
 5.3.2. Dummy Variables --
 5.3.3. Interaction --
 5.3.4. Variable Selection --
 5.4. Diagnostics --
 5.4.1. Outliers --
 5.4.2. Influential Observations --
 5.4.3. Durbin-Watson Statistic --
 5.5. Weighted Regression --
 5.6. Logistic Regression --
 5.6.1. Dichotomous Logistic Regression --
 5.6.2. Multinomial Logistic Model --
 5.6.3. Cumulative Logistic Model --
 5.7. Poisson Regression --
 5.8. Robust Regression --
 5.9. Nonlinear Regression --
 5.10. Piecewise Regression --
 5.11. Accelerated Failure Time (AFT) Model --
 5.12. Cox Regression --
 5.12.1. Proportional Hazards Model --
 5.12.2. Proportional Hazard Assumption --
 5.12.3. Stratified Cox Model 5.12.4. Time-Varying Covariates --
 5.12.5. Competing Risks --
 5.13. Parallelism of Regression Equations --
 5.14. Variance-Stabilizing Transformations --
 5.15. Ridge Regression --
 5.16. Local Regression (LOESS) --
 5.17. Response Surface Methodology: Quadratic Model --
 5.18. Mixture Designs and Their Analysis --
 5.19. Analysis of Longitudinal Data: Mixed Models --
 6. Miscellaneous Topics --
 6.1. Missing Data --
 6.2. Diagnostic Errors and Human Behavior --
 6.2.1. Introduction --
 6.2.2. Independent Samples --
 6.2.2.1. Two Independent Samples --
 6.2.2.2. k Independent Samples --
 6.2.3. Two Dependent Samples --
 6.2.4. Finding the Threshold for a Screening Variable --
 6.2.5. Analyzing Response Data with Errors --
 6.2.6. Responders' Anonymity --
 6.3. Density Estimation --
 6.3.1. Parametric Density Estimation --
 6.3.2. Nonparametric Univariate Density Estimation --
 6.3.3. Bivariate Kernel Estimator --
 6.4. Robust Estimators 6.5. Jackknife Estimators --
 6.6. Bootstrap Method --
 6.7. Propensity Scores --
 6.8. Interim Analysis and Stopping Rules --
 6.8.1. Stopping Rules --
 6.8.2. Conditional Power --
 6.9. Microarrays and Multiple Testing --
 6.9.1. Microarrays --
 6.9.2. Multiple Testing --
 6.10. Stability of Products --
 6.11. Group Testing --
 6.12. Correspondence Analysis --
 6.13. Classification Regression Trees --
 6.14. Multidimensional Scaling --
 6.15. Path Analysis --
 6.16. Choice-Based Conjoint Analysis --
 6.16.1. Availability Designs and Cross Effects --
 6.16.2. Pareto-Optimal Choice Sets --
 6.16.3. Mixture-Amount Designs --
 6.17. Meta-Analysis --
 6.17.1. Homogeneity of the Effect Sizes --
 6.17.2. Combining the p-Values.