Estimating treatment effects in clinical crossover trials

Some current approaches to modeling crossover trials in two treatments are critically reviewed from the perspective of the practical requirements of the drug developer. Particular attention is paid to the AB/BA design, and the inadequacies of the once popular two-stage procedure are discussed in detail. The use of baseline data is also examined. Both frequentist and Bayesian alternatives to approaches currently advocated are considered and critically compared. It is concluded that it is crucial for the applied statistician working in this field to have an appreciation of the practical medical and pharmacological background.

Bayesian analyses of two-treatment crossover studies

This review covers Bayesian analyses of two-treatment crossover studies. The main emphasis is placed on the analysis of continuous data although we also consider dichotomous responses. Studies discussed include (1) the simple two-period, two-treatment crossover, (2) the two-period crossover with one baseline measurement, (3) the two-period crossover with two baselines and (4) the extra-period design with two treatment sequences.

Angina: evolution of the role of nitrates

In recent years, concern has been expressed over attenuation of therapeutic effect in patients receiving continuous nitroglycerin therapy for the treatment of angina. Studies have shown that exercise tolerance time does not improve with continuous nitroglycerin regimens, although the frequency of anginal attacks may decrease. Intermittent therapy, which incorporates a nitrate-free interval, improves both exercise time and clinical angina. The optimal duration of the nitrate-free interval has yet to be determined. Future research is likely to focus more on supply-side factors in angina. Of the available antianginal drugs, nitrates have been shown to be highly effective coronary vasodilators, particularly in areas of stenosis.