PART 1. FUNDAMENTALS
1 • Randomized Explanatory Trials
            RET Framing Using Mediation and Moderation
            RETs Instead of RCTs
            Facets of an RET
            The Big Picture
            Experimental Therapeutics
            Mixed Methods RETs
            RETs as Thought Experiments
            Factorial RETs and Dismantling Designs
            RETs and Other Facets of Program Design and Evaluation
2 • Conceptual Fundamentals for RETs
            The Nature of Causality
            Influence Diagrams as a Theoretical Tool for RETs
            Thinking of RETs as Opening the Black Box
            Task 1: Conceptually Mapping the Intervention
            Task 2: Broader Analysis of Outcomes, Mediators and Moderators
            Task 3: Defining Meaningful Effects in RETs
            Multiple Outcome Research
3 • Measurement Fundamentals for RETs
            Concept-Measurement Mapping
            Measurement Metrics
            Measurement Error
            The Facets of Measurement
            Cronbach's Alpha and Issues of Dimensionality
            Other Criteria for Choosing a Measure
            Latent Variable Representations of Constructs
            Formative Measurement and Composites
            Using Single versus Multiple Indicators of Constructs
            Measurement Invariance
            Measurement-Intervention Correspondence: Creating Study Specific Measures
            False Dichotomization of Measures
            Baseline Assessments: Do We Collect Them or Not
            Frequency and Timing of Assessments
4 • Methodological Fundamentals for RETs
            Types of Randomized Trials
            Randomized Trial Designs
            Populations for Randomized Trials
            The Concept of Imbalance
            Randomization Strategies
            Phases of a Randomized Trial
            Demand Characteristics and Blinding
            Treatment Integrity
            The Consort Checklist
            Appendix: Competing Components in RETs
5 • Statistical Fundamentals for RETs: Regression Modeling
            The Basics of Linear Regression
            The Basics of Binary Regression
            The Basics of Ordinal Regression
            The Basics of Multinomial Regression
            The Basics of Discrete/Count Regression
            Appendix: Latent Propensity Models for Binary Regression
6 • Statistical Fundamentals for RETs: Advanced Topics
            Non-Linear Regression
            Outlier Resistant Robust Regression
            The Problem of Multiple Significance Tests
            Margins of Error
            Sensitivity Analyses
            Endogeneity
            Centering Variables
            Profile Analysis
7 • Statistical Fundamentals for RETs: Structural Equation Modeling
            The Basics of SEM
            Tautological Predicted and Observed Covariances
            Maximum Likelihood Estimation
            Indices of Model Fit and Model Testing
            Localized Fit Indices
            Evaluation of Predicted Paths
            A Weight-of-the-Evidence Perspective
            Latent Variables in SEM
            Comparing Models using SEM
            Theory Revisions Based on Data
8 • Statistical Fundamentals for RETs: Non-Traditional Structural Equation Modeling
            Bayesian SEM
            Limited Information SEM
            Structural Causal Modeling

PART II. MEDIATION ANALYSIS IN RETs
9 • Mediation Analysis in RETs: Basic Approaches
           Classic Mediation Analysis Approaches
           The Baron and Kenny Method
           The Coefficient Product Method
           The Joint Significance Test
           Hayes Conditional Process Analysis
           The MacArthur Network Model
           Causal Mediation Analysis
           Structural Equation Modeling
10 • Evaluating Effect Sizes in RETs
           Indices of Effect Size in RETs
           Setting Effect Size Standards in RETs
           Effect Size Interpretation and Sampling Error
           Appendix: Calculation of Effect Sizes
11 • Mediation Analysis with Continuous Outcomes
           A Numerical Example
          The Model Equations
          Preliminary Analyses
          Traditional Full Information SEM Analysis
          Bayesian SEM
          Limited Information SEM
          Causal Mediation Analysis
          Specification Error and Result Generalizability
12 • Mediation Analysis with Binary Outcomes
          Mediation Analysis with Binary Outcomes
          Broader Perspectives on Modeling Binary Outcomes
          Numerical Example with a Binary Outcome
          LISEM Analysis: The Modified Linear Probability Model
          LISEM Analysis: The Probit Model
          FISEM Analysis: Probit Modeling
          FISEM Analysis: Bayesian Modeling
          FISEM Analysis: The Modified Linear Probability Model
          Supplemental Analyses
          Binary Mediators and Latent Variables
          Appendix A: Calculation of Average Marginal Effects
          Appendix B: Setting Meaningfulness Standards
13 • Mediation Analysis with Ordinal and Nominal Outcomes
          Numerical Example of Ordinal Outcomes
          Ordinal Modeling: Overview of the Probability Approach
          Preliminary Analyses
          Ordinal Modeling: Application of the Probability Approach
          Ordinal Modeling: The Latent Response Approach
          Ordinal Mediators and Latent Variables with Multiple Indicators
          Concluding Comments on the Analysis of Ordinal Outcomes
          Nominal/ordinal Outcomes: The Multinomial Model
          Concluding Comments
          Appendix: Alternative Parameterizations
14 • Mediation Analysis with Count Outcomes
          [To be added]
15 • Non-linear and Specialized Modeling in Mediation Analysis
          Mediation Analysis and Polynomial Regression
          Mediation Analysis and Spline Regression
          Mediation Analysis and Traditional Non-linear Regression
          Mediation Analysis and Bayes Additive Regression Trees
          Mediation Analysis and Generalized Additive Models
          Mediation Analysis and Recursuve Partitioning (CART) Models
          Mediation Analysis and Cluster Analysis
          Mediation Analysis and Latent Profile/Class Analysis
          Concluding Comments
          Appendix A: Calculation of AME for a Quadratic Model
          Appendix B: Elaboration of Exponential Function
          Appendix C: Geweke Test of Convergence
16 • RETs with Follow-Ups: Longitudinal Modeling
          [to be added]
17 • Mediator Relative Importance and Exploratory Mediation Analysis
          Relative Importance of Omnibus Mediation Effects
          A Numerical Example
          Tests of Relative Importance of Omnibus Mediation Effects
          Tests of Relative Importance of Mediator Effects on Outcomes
          When the Number of Mediators is Large: Data Reduction

PART III. MODERATION ANALYSIS IN RETs
18 • Introduction to Moderation Analysis
          Moderation Analysis in RETs
          When Change Does Not Reflect Treatment Response: Implications for Moderation Analysis
          Parameterizing Moderated Relationships
          When X Moderates Itself in the X-Y Relationship
          Graphing Moderated Relationships
          Ordinal and Disordinal Moderation
          Asserting Group Equivalence
19 • Moderation Analysis with Product Terms
          [to be added]
20 • Moderation Analysis with Multiple Groups
          [to be added]
21 • Exploratory Moderation Analysis and Non-Linear Dynamics
          [to be added]
22 • Moderated Mediation in RETs
          [to be added]
23 • Mediated Moderation in RETs
          [to be added]
24 • Moderated Moderation in RETs
          [to be added]

PART IV. ADDITIONAL ISSUES IN THE ANALYSIS OF RETs
25 • Group Administered Interventions and Cluster Designs
          Sampling/Experimental Design and Custering
          Clusters as a Nuisance or as Theoretically Meaningful
          Hierarhcial Structure of Clusters
          Multilevel Equations
          The Intraclass Correlation Coefficient
          Design Effects
          Cluster Populations
          Numerical Examples
          Clustering as a Nuisance
          Multilevel SEM
          Analysis Strategies When There Are Few Clusters
          Power Analysis/Simulations for Cluster Randomized Trials
          Methodological Issues in Cluster Randomized Trials
26 • Missing Data
          Traditional Approaches to Missing Data
          Missing Data Mechanismss
          Assessment of Bias in Missing Data
          Missing at Random is a Matter of Degreep
          Missing Data Bias is Not Always Bad
          Patterns of Missing Data
          A Numerical Example
          Modern Strategies for Dealing with Missing Data
          Additional Issues in Handling Missing Data
          Listwise Missing Data Methods Revisited
          Which Method is Best?
          When Data are Not MCAR or MAR
          Missing Data Simulations
27 • Intent to Treat and Per Protocol Modeling
          Intoduction
          Implementation Trials
          The Complier Average Causal Effect (CACE) Framework
          Treatment Confounds
          Numerical Example
          Efficacy Focused Analyses
          Effectiveness Focused Analyses
          Extensions to Randomized Explanatory Trials
          Appendix: Detailed CACE Output
28 • Sample Size Considerations
          Intoduction
          Sampling Error
          Sample Size and Properties of Estimators
          Sample Size and Asymptotic Theory
          Sample Size, Covariance Properties, and Model Complexity
          Implications for Sample Size Decisions
          Sample Size and Statistical Power
          Sample Size and Margins of Error
          Localized Simulations for Sample Size Decisions
          Small Sample Statistical Tests
          Appendix: Specifying Standardized Metric Population Values
29 • Factorial and Dismantling Designs, Multi-Treatment RETs
          [to be added]
30 • Epilogue
          [to be added]





M