Search results

When a panel is composed of residents from three or four of the conventionally defined Canadian regions, the issue of whether or not regionalism still persists in Canada is already to a large extent prejudged. For this reason, and also because I am doubtful of my credentials as either an interpreter or bearer of any particular set of regional values, I propose to address myself to the problem of how one can measure regional effects.

Log-linear methods provide a powerful framework and the statistical apparatus for rigorously analyzing categorical data. These methods were introduced and developed by Leo Goodman and others in the early 1970s. In the late 1970s and the early 1980s, Goodman, Alan Agresti, Clifford Clogg, Otis Dudley Duncan, and others showed how these models could help us to estimate associations between discrete variables, including ordered and unordered polytomies. The last decade has witnessed a set of diverse extensions of these techniques. This paper reviews the basic log-linear strategy and illustrates key concepts. Citations are given to other articles on these topics, many of which are nontechnical and contain substantive sociological applications.

This article explores the S-plus statistical computing environment in the context of an analysis of Duncan's occupational prestige data. The article highlights the modeling and graphics capabilities of S-plus and introduces basic programming concepts. In the course of the analysis, the authors develop functions for bootstrapping and kernel density estimation. In addition, they display some of the extensive interactive graphics capabilities of S-plus.