For the study of cardiovascular disease, for instance, hypertension and angina pectoris, properly de signed crossover studies are to be preferred over parallel-design stud ies. Many statisticians now propose that these studies should always be tested for carryover effects. In the present paper the author analyzes the crossover studies published after No vember, 1985, in two general and two specialist journals (New England Journal of Medicine, Lancet, Angiol ogy, British Heart Journal). Of 73 pa pers only 23 (32%) consider the possi bility of carryover effects. Of these latter papers 12 (16%) perform sta tistical tests for these effects. The results of these tests were shown in only 7 papers (10%). It is concluded that there is a discrepancy between the statistical recommendations and the data presented in the literature.
Get full access to this article
View all access options for this article.
References
1.
Harrison DC: Clinical testing of beta-adrenergic blockade in angina pectoris. In: Laboratoires d' Etudes et de Recherches Synthelabo, Vol 1, ed. by Morselli PL, Kilborn JR, Cavero L, et al. New York: Raven Press, 1983, pp 243-250.
2.
van Lier HJ, Cleophas TJ: The crossover design in cardiovascular research. Abstract book, Annual Meeting, International College of Angiology, Montreux, Switzerland, Aug 1987, p 41, ed. by the International College of Angiology, Roslyn, N.Y.
3.
Willan AR, Pater JL: Carryover and the two-period clinical trial. Biometrics42:593-599, 1986.
4.
Cleophas TJ, Bailar JC: Statistical concepts fundamental to investigations. N. Engl J Med313:1026, 1985.
5.
Pocock SJ, Hughes MD, Lee RJ: Statistical problems in the reporting of clinical trials. N Engl J Med317:426-432, 1987.
6.
Hills M., Armitage P.: The two-period cross-over trial. Br J Clin Pharmacol8:7-20, 1979.
7.
Brown BW: The crossover experiment for clinical trials. Biometrics36:69-79, 1980.
8.
Barker M., Hews RJ, Huitson A., et al: The two period cross-over trial. BIAS9:67-112, 1982.
9.
Louis TA, Lavori PW, Bailar JC, et al: Crossover and self-controlled design in clinical research. N Engl J Med310:24-31, 1984.
10.
Prescott RJ : The comparison of success rates in crossover trials in the presence of an order effect. J Stat Soc Series C, Appl Stat30:9-15, 1981.
11.
Lachin JM: Introduction to sample size determination and power analysis for clinical trials. Controlled Clinical Trials2:93-113, 1981.
12.
Cox DR: Planning of Experiments. New York: Wiley, 1958.
13.
Grizzle JE: The two-period change-over design and its use in clinical trials. Biometrics21:469-480, 1965. Corrigenda in Biometrics30:727, 1974.
14.
Koch GG: The use of non-parametric methods in the statistical analysis of the two-paired change-over design. Biometrics28:577-584, 1972.
15.
Gart JJ: An exact test for comparing matched proportions in cross-over designs. Biometrika56:75-80, 1969.
16.
Wallenstein S., Fisher AC: The analysis of the two-period repeated measurements cross-over design with application to clinical trials. Biometrics33:261-269, 1977.
17.
Cleophas TJ , van Lier HJ, Fennis JF, et al: Treatment of Raynaud's syndrome with adrenergic alpha-blockade with or without beta-blockade. Angiology35:29-36, 1984.
