August 2009
Intermediate to advanced
648 pages
17h 35m
English
Analysts are sometimes interested in assessing the strength of association in the s × r table. Although there is no counterpart to the odds ratios in 2 × 2 tables, there are several measures of association available, and, as you might expect, their choice depends on the scale of measurement.
If the data in the table have an interval scale or have scores that are equally spaced, then the Pearson correlation coefficient is an appropriate measure of association, and one that is familiar to most readers.
If the data do not lie on an obvious scale, but are ordinal in nature, then there are other measures of association that apply. The Spearman rank correlation coefficient is produced ...
Read now
Unlock full access