STAT 560 / CS&SS 560

Hierarchical Modeling for the Social Sciences

Elena Erosheva
C 14-C Padelford Hall
(206) 685-0166
elena@stat.washington.edu

Preliminaries

  • Quarter: Winter 2005
  • Class times: TTh 9:30 - 11:20
  • Place: PAR 206 (except during computer practice sessions on Th: SAV 137)
  • Office hours: Th 1:00-2:00, or by appointment
  • Web: follow the course link from my homepage at http://www.stat.washington.edu/elena 

Course description

A great deal of data analyzed by social scientists are organized according to some sort of clustered or hierarchical structure. This course will focus on methodology for the analysis of data with complex patterns of variability such as those arising from longitudinal and nested designs: e.g., measurements on subjects over time, or records on students within classes within schools. The goal of this course is to provide students with knowledge and confidence to use hierarchical modeling in their discipline through understanding of statistical theory behind hierarchical models set up and estimation. We will spend a fair amount of time during the quarter through the underlying mathematics of hierarchical models. Nonetheless, the main emphasis of the class will be on applications. 

Prerequisites

It is assumed that the students have completed a statistical sequence (such as SOC 424-426), and a regression or an applied regression course (such as CS&SS 504). It is also recommended that the students have some familiarity with basic calculus (differentiation and integration), matrix algebra (matrix addition, multiplication, and inversion), and probability theory. Some familiarity with computing packages SAS and S-Plus or R would be helpful as well.

Computing

We will use R/S-plus software for creating plots and for exploratory data analysis. We will mostly use SAS Proc Mixed for fitting the models.

Course materials

Required text:

  • Multilevel Analysis: An Introduction to Basic and Advanced Multilevel Modeling (1999), Roel J. Bosker and Tom A. B. Snijders. 
  • SAS System for Mixed Models (1996) Ramon C. Littell, George A. Milliken, Walter W. Stroup, Russell Wolfinger.

Optional text:

  • SAS for Linear Models (2002) Ramon C. Littell, Walter W. Stroup, Rudolf J. Freund.
  •  Analysis of Longitudinal Data (2002) Peter Diggle (Editor), Patrick Heagerty, Kung-Yee Liang, Scott Zeger. 
  • Linear Mixed Models for Longitudinal Data (2000) Geert Verbeke, G. Molenberghs, P. Bickel (Editor), P. Diggle (Editor).
  • Mixed Effects Models in S and S-Plus (2000) Jose C. Pinheiro, Douglas M. Bates.
  • Hierarchical Linear Models: Applications and Data Analysis Methods (2002) Stephen W. Raudenbush and Anthony S. Bryk.

Homework assignments and grades

  • Final grades for this course will be based on homework assignments and a take-home final exam. The final exam will be worth up to two homeworks.
  • I encourage you to work on the homework assignments with each other in small groups. However, each student is required to prepare and submit their own solutions and write-up. Homework will be assigned about every one to two weeks. Homework assignments that are not handed in on time will receive zero points (except in case of documented emergency).
  • Please type up your homework assignments using a text editor. Unless specifically requested, never submit raw computer output pages. Instead, cut out the appropriate parts of the output and neatly tape it onto your homework paper (or better yet, insert appropriate parts of the output into your write-up). Please label all output, plots, variables, etc., appropriately. 
  • The final exam will be a take-home cumulative exam.
Students with Disabilities: If you would like to request academic accommodations due to a disability, please contact Disabled Student Services, 448 Schmitz, 543-8924 (V/TTY).  If you have a letter from Disabled Student Services indicating you have a disability that requires academic accommodations, please present the letter to me so we can discuss the accommodations you might need for this class.