Multilevel/Hierarchical Models

 

Introductory Statistics with R

 

Applied Longitudcinal Data Analysis

 

The R Book

 

Longitudinal Methods

 

Handbook of Multilevel Analysis

 

Designing Experiments

Multilevel/Hierarchical Models
David R. Cross, Ph.D.

Course Overview

This course is a thorough introduction to multilevel/hierarchical linear models (HLM), using the open-source computational software R and BUGS. Course objectives include the following:

  • Students will be able to read and understand published articles using HLM.
  • Students will become aware of the varied (appropriate) applications of HLM in the behavioral sciences.
  • Students will be able to analyze their own data using HLM and the R software package.
  • Students will understand the conceptual foundations for appropriately analyzing data using HLM.

The instructor is available by appointment, and can be contacted by email (d.cross@tcu.edu). The textbooks for the course are:

  • Gelman, A., & Hill, J. (2007). Data Analysis Using Regression and Multilevel/Hierarchical Models. Cambridge University Press.
  • Dalgaard, P. (2008). Introductory Statistics with R (2nd ed.). Springer.
  • Singer, J. D., & Willett, J. B. (2003). Applied Longitudinal Data Analysis: Modeling Change and Event Occurrence. Oxford University Press.

The course is offered during the eight-week evening term, and students are expected to turn in one assignment each of the eight weeks. In addition, students are expected to give two presentations to the class: One presentation on a published study using multilevel/hierarchical linear models, and one presentation on a data analysis project conducted by the student. Each assignment is worth 10 points, and students must earn 85 points for an A, and 70 points for a B.

Here are some helpful websites:

Students should have taken at least two courses in quantitative methods prior to enrolling in this class. The class meets twice per week, according to the following schedule of topics and readings:

Week 1

  • Introduction to Multilevel Models (MLM), R, and BUGS
    • Dalgaard: Chapters 1 & 2
    • Gelman & Hill: Chapter 1
    • Singer & Willett: Chapter 1
  • Review: Probability and Statistics
    • Dalgaard: Chapters 3–5
    • Gelman & Hill: Chapter 2
  • Assignment: Dalgaard, Chs. 1–5, Odd Exercises

Week 2

  • Review: Regression Basics
    • Dalgaard: Chapter 6
    • Gelman & Hill: Chapter 3
  • Review: Fitting Regression Models
    • Dalgaard: Chapter 11 & Sections 12.1–5
    • Gelman & Hill: Chapter 4
    • Singer & Willett: Chapter 2
  • Assignment: Gelman & Hill, Chs. 3 & 4, Odd Exercises

Week 3

  • Simulation and Regression Inference
    • Gelman & Hill: Sections 7.1–3, 8.1–3
  • Causal Inference and Regression Models
    • Gelman & Hill: Chapter 9 & Sections 10.1–4
  • Assignment: Gelman & Hill, Exercises 7.1, 8.1, 9.6–11, 10.1

Week 4

  • Multilevel Structures
    • Gelman & Hill: Chapter 11
    • Singer & Willett: Chapter 3
  • Multilevel Linear Models
    • Gelman & Hill: Chapters 12 & 13
    • Singer & Willett: Chapter 4
  • Assignment: Gelman & Hill, Exercises 11.4, 12.1–3, 13.5

Week 5

  • MLM in BUGS and R
    • Gelman & Hill: Chapter 16 & Sections 17.1–3
  • Modeling Time and Change
    • Singer & Willett: Chapters 5–7
  • Assignment: Gelman & Hill, Exercises 16.1–5, 17.1–3

Week 6

  • Debugging and Speeding Convergence
    • Gelman & Hill: Chapter 19
  • Data Collection and Statistical Power
    • Dalgaard: Chapter 9
    • Gelman & Hill: Chapter 20
  • Assignment: Gelman & Hill, Exercises 19.1–2, 20.5–6

Week 7

  • Understanding and Summarizing Fitted Models
    • Gelman & Hill: Chapter 21
  • Analysis of Variance
    • Dalgaard: Chapter 7, Sections 12.6–8
    • Gelman & Hill: Chapter 22
  • Assignment: Gelman & Hill, Exercises 21.1, 21.3, 22.1 (see 17.1–3)

Week 8

  • Causal Inference and Model Comparison
    • Gelman & Hill: Chapter 23 & 24
  • Missing Data
    • Gelman & Hill: Chapter 25
  • Assignment: Gelman & Hill, Exercises 23.1, 25.2

Acknowledgements

All of the software used to create the slides posted here is free software, and includes the following:

Note: I am currently revising the course structure and the lecture slides—new slides will be posted asap!

Class Photos

  • Summer 2009

Home | Research | Lab | Publications | Classes | Links