Multilevel Modeling

Chapter 1. General Introduction
1.1 Nested Data Structures
1.2 Why Conventional Statistics are Inappropriate for Nested Data
1.3 Methods for Analyzing Nested Data

Chapter 2. Basic Multilevel Models
2.1 The Random-Effects ANOVA Model
2.2 Incorporating Lower-Level Predictors
2.3 Incorporating Upper-Level Predictors

Chapter 3. Decomposing Between- and Within-Group Effects
3.1 Total, Between-Group and Within-Group Effects
3.2 Centering Level 1 and Level 2 Predictors
3.3 Example: Effects of Centering
3.4 Frequently Asked Questions

Chapter 4. Random Slopes and Cross-Level Interactions
4.1 Including Random Slopes for Level-1 Predictors
4.2 Example: Random Slopes
4.3 Modeling Cross-Level Interactions
4.4 Example: Cross-Level Interaction

Chapter 5. Model Assumptions and Model Evaluation
5.1 Model Assumptions
5.2 Model Assessment and Diagnostics
5.3 Maximum Likelihood Estimation

Chapter 6. The Analysis of Repeated Measures: Part 1
6.1 Growth Curves Within the Multilevel Framework
6.2 Alternative Metrics of Time
6.3 Alternative Level-1 Error Structures
6.4 Modeling Non-Linear Change

Chapter 7. The Analysis of Repeated Measures: Part 2
7.1 Time-Invariant Predictors of Growth
7.2 Multiple Groups Models
7.3 Time-Varying Covariates

Chapter 8. Multilevel Models for Intensive Longitudinal Data
8.1 Unique Features of Intensive Longitudinal Data
8.2 Modeling Time Trends
8.3 Serially Correlated Residuals
8.4 Within- and Between-Person Effect Decomposition

Chapter 9. The Analysis of Three-Level Data
9.1 Three-Level Models for Hierarchical Data
9.2 Three-Level Models for Longitudinal Data

Chapter 10. Multilevel Models for Discrete Outcomes
10.1 Discrete Dependent Variables
10.2 Generalized Linear Models
10.3 Multilevel Generalized Linear Models
10.4 Additional Considerations

Appendix A. Multilevel Mediation

Appendix B. Multivariate Multilevel Models

Appendix C. Cross-Classified Models

Our workshop is designed for graduate students, post-doctoral fellows, faculty, and research scientists from the behavioral, social, and health sciences. Although it is recommended that participants have a working knowledge of the general regression model, these core concepts will be reviewed at the beginning of the workshop. Participants who would like a more thorough refresher on linear regression prior to attending may wish to watch our (no cost) Linear Regression Playlist on YouTube.

Software demonstrations will be provided in R, SAS, SPSS, and Stata. While it is helpful to have some familiarity with one of these programs, this is not necessary. The lectures which constitute the majority of the workshop are software-independent

Dan Bauer and Patrick Curran co-teach the workshop and alternate lecturing throughout the day. Participants will receive approximately 35 hours of total lecture time as well as PDF copies of the course notes and the computer demonstrations as well as data and code for all examples. The PDFs are not time-limited and may be retained indefinitely but should not be distributed to others without obtaining prior permission.

Please see sample copies of the lecture notes and SAS software notes (parallel versions exist in R, SPSS, and Stata).

Learn more about what makes our training unique...