This is the program for the 2010 Joint Statistical Meetings in Vancouver, British Columbia.
|CE_14C||Mon, 8/2/2010, 8:30 AM - 5:00 PM||CC-11(East)|
|Analysis of Ordinal Categorical Data — Continuing Education Course|
|Instructor(s): Alan Agresti, University of Florida, Bhramar Mukherjee, University of Michigan|
|This course surveys methods for analyzing ordinal categorical data, with main focus on models for ordinal response variables. Topics to be covered include ordinal odds ratios and association measures for contingency tables, logistic regression models using cumulative logits, other ordinal logistic regression models (adjacent-categories logits, continuation-ratio logits, partial proportional odds, non-proportional odds, stereotype model), other multinomial response models (cumulative probit, log-log, mean response), marginal models and random effects models for clustered ordinal responses, and Bayesian approaches. Examples use SAS (PROC GENMOD, LOGISTIC, and NLMIXED) and references will be given for R functions and Stata procedures. The presentation emphasizes interpretation of the methods rather than technical details, with examples including randomized clinical trials and social surveys such as the General Social Survey. Attendees are expected to have some familiarity with basic methods of categorical data analysis, including logistic regression models and chi-squared tests, such as presented in the first four chapters of Agresti's text "An Introduction to Categorical Data Analysis."|