- Home
- About Us
- Workshops & Seminars
- Software Help
- Software Access
- Spatial Analysis / GIS
- External Resources
3550 Rackham Building University of Michigan Ann Arbor, MI 48109-1070 cscar@umich.edu
more info
Regression for Non-Normally Distributed Data
using SAS
June 1 and 2, 2005
Brenda Gillespie and Kathy Welch
Many statistical techniques (ordinary least squares regression, ANOVA, ANCOVA) are based on normally distributed dependent variables. However, data that are not normally distributed are commonly encountered. These include binary outcomes (whether a pregnant woman went to the prenatal clinic or not), count data (number of children a woman had) and categorical data (type of car a person buys). Generalized linear models are appropriate for all of these types of outcomes, and for normally distributed responses. When there is clustered data, repeated measures, or longitudinal data, the correlations among observations on the same unit need to be taken into account.
This two-day workshop will cover uses of the Generalized Linear Model for cross-sectional data and GEE (Generalized Estimating Equations) for clustered, repeated measures or longitudinal data. Logistic regression, Poisson regression and loglinear models will be discussed. Instruction emphasizes when to use each method, as well as interpretation of SAS output and checking for model appropriateness. There will be a morning lecture and an afternoon hands-on lab, using SAS Proc Genmod to analyze real data sets.
- Instructors
- Brenda Gillespie is the Associate
Director of CSCAR and Assistant Professor in the Department of
Biostatistics at The University of Michigan. She has extensive
experience as a statistical consultant, and specializes in the
various methods for analysis of censored data.
Kathy Welch is a Statistical Consultant and primary SAS Consultant for CSCAR. She consults at CSCAR on linear regression, Poisson regression, and analysis of cluster or longitudinal data. Kathy also teaches a course in statistical computing for the School of Public Health. - Audience
- Researchers in applied fields who may encounter data suitable for Generalized Linear Models.
- Prerequisite
- Introductory statistics, familiarity with multiple regression and correlation, experience with SAS or other statistical software, experience with computers running Windows.
- Provisions
- Enrollees receive lecture notes, a bibliography, and example computer package commands and output. Morning refreshments provided. Break time for off-site lunch (lunch not provided); many restaurants nearby.
- Dates & Times
- June 1 and 2, 2005, 8:30 AM - 5:00 PM
- Location
-
- Morning Lecture: 8:30 AM - 12:00 PM
- School of Public Health II, Room M1170
- Afternoon Lab Session: 1:00 PM - 5:00 PM
- School of Public Health II, Computing Classroom C
- Fees
- $250 for University of Michigan affiliated faculty, staff and students
- $600 for others
Registrations on or before May 17, 2005 - $300 for University of Michigan affiliated faculty, staff and students
- $720 for others
Registrations after May 17, 2005 Please make check payable to CSCAR-University of Michigan, or give the University of Michigan Project/Grant or shortcode to be billed. Send check to CSCAR, 3550 Rackham Bldg., University of Michigan, 915 E. Washington St., Ann Arbor, MI, 48109-1070.
- Registration
- Call CSCAR at 734-764-7828. Enrollment is limited to 21 participants.