In a longitudinal study of the health effects of air pollution (Ware, Lipsitz, and Speizer 1988), children were examined annually at ages 9, 10, 11, and 12. At each examination, the response measured was the presence of wheezing. Two questions of interest are
Does the prevalence of wheezing change with age?
Is there a quantifiable trend in the age-specific prevalence rates?
Table 14.5 [*], from Agresti (1990, p. 408), displays data from 1019 children included in this study. In this single population example, the cross-classification of a dichotomous outcome at four time points defines r = 24 = 16 response ...