13.8. Modeling Rank Measures of Association Statistics
Many studies include outcomes that are ordinal in nature. When the treatment is either dichotomous or ordinal, you can model rank measures of correlation using WLS methods and use that framework to investigate various treatment effects and interactions. Such an analysis can often complement statistical models such as the proportional odds model. Refer to Carr, Hafner, and Koch (1989) for an example of such an analysis applied to Goodman-Kruskal rank correlation coefficients, also known as gamma coefficients.
The Mann-Whitney rank measure of association statistics are useful statistics for assessing the association between an ordinal outcome and a dichotomous explanatory variable. Consider ...
Get Categorical Data Analysis Using The SAS® System, 2nd Edition now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
