ABSTRACT
In a clinical trial reported by Thall and Vail (1990), 59 patients with epilepsy were randomized to groups receiving either the anti-epileptic drug progabide or a placebo in addition to standard chemotherapy. The number of seizures was counted over four two-week periods. In addition, a baseline seizure rate was recorded for each patient, based on the eight-week prerandomization seizure count. The age of each patient was also recorded. The main question of interest is whether the treatment progabide reduces the frequency of epileptic seizures compared with placebo. The data are shown in Table 10.1. (These data also appear in Hand et al., 1994.)
In this chapter we consider an approach to the analysis of longitudinal data that is very different from random effects modeling described in the previous chapter. Instead of attempting to model the dependence between responses on the same individuals as arising from betweensubject heterogeneity represented by random intercepts and possibly random slopes, we will concentrate on estimating the marginal mean structure, treating the dependence as a nuisance.
