RSSeNEWS to be determined...

The Society's Professional Development Centre is planning to run a 2 day course on Analysis of Ordinal Categorical Data on 20 and 21 July 2011 in London.

Categorical data are common. When there are more than two categories, those categories usually have an ordering. Using ordinary regression methods for such data can be biased. It is useful for a methodologist to know the various options for analyzing such data as well as the pros and cons of those approaches.

The main objective of this course will be to extend attendees' knowledge in categorical data analysis to methods that utilize the ordinality of a response variable. Attendees will learn the advantages of such analyses relative to standard analyses (e.g., Pearson's chi-squared test, baseline-category logit models) that ignore the ordering. The course includes sessions on logistic regression models using cumulative logits, other ordinal logistic models, other ordinal multinomial models and modelling clustered ordinal responses. The main emphasis is on introducing various ordinal models and their interpretations rather than technical or theoretical issues. Through examples, attendees will learn how to use the models and weigh the advantages and disadvantages of the various model types.

Course presenter

Alan Agresti is Distinguished Professor Emeritus in the Department of Statistics at the University of Florida. He has written five books, including "Categorical Data Analysis," which has received more than 10,000 citations in journal articles.

He received an Honorary Doctor of Science from De Montfort University in 1999, the Statistician of the Year Award from the Chicago ASA chapter in 2003, and the first Herman Callaert Leadership Award from Hasselt University, Belgium in 2004.

Places will be limited and we expect this to be a very popular event. If you would like to attend, please register your initial interest by e-mailing courses@rss.org.uk Those who have pre-registered will be given priority once registration opens.