Clinical trials without statistical significance. The importance of type II error

Roberto Anaya-Prado; Fernando Grover-Páez; Ninel Mayari Centeno-López; Marisol Godínez-Rubí

2008, Number 3

<< Back

Cir Cir 2008; 76 (3)

Clinical trials without statistical significance. The importance of type II error

Anaya-Prado R, Grover-Páez F, Centeno-López NM, Godínez-Rubí M

Full text

How to cite this article

Language: Spanish
References: 13
Page: 271-275
PDF size: 61.72 Kb.

ABSTRACT

A randomized clinical trial is a prospective experiment to compare one or more interventions against a control group in order to determine the effectiveness of the interventions. A clinical trial may compare the value of a drug vs. placebo. It may compare surgical with medical interventions. The principles apply to any situation in which the issue of who is exposed to which condition is under the control of the experimenter, and that the method of assignment is through randomization. A negative clinical trial is that in which no significant difference is found between the comparison groups. Results without statistical difference may be useful either to discard useless treatments or to demonstrate that one intervention is as effective as the one it was compared with. Eliminating useless treatments may be adequate. However, if this is the result of studies with methodological errors, new interventions that are actually useful may not be available for patients. In this review we present some of the possible methodological errors that may lead to false negative results in clinical trials.

REFERENCES

1. Hanley JA, Lippman-Hand A. If nothing goes wrong, is everything all right? JAMA 1983;249:1743-1745.
2. López-Jiménez F, Paniagua D, Lamas GA. Interpretación de ensayos clínicos negativos o sin diferencia. En: López-Jiménez F, ed. Manual de medicina basada en evidencia. México: El Manual Moderno/JGH Editores;2001. pp. 99-109.
3. Greenberg RS, Daniels SR, Flanders WD, Eley JW, Boring JR. Interpretation of epidemiologic literature. In: Greenberg RS, ed. Medical Epidemiology. 3rd ed. New York: McGraw-Hill;2001. pp. 175-188.
4. Freiman JA, Chalmers TC, Smith H, Kuebler RR. The importance of beta, the type II error and sample size in the design and interpretation of the randomized controlled trial. N Engl J Med 1978;299:690-694.
5. Moher D, Dulberg CS, Wells GA. Statistical power, sample size, and their reporting in randomized controlled trials. JAMA 1994;272:122-124.
6. Dean AG, Dean JA, Burton AH, Dicker RC. Epi Info: a general-purpose microcomputer program for public health information systems. Am J Prev Med 1991;7:178-182.
7. Grimes DA, Schulz KF. Clinical research in obstetrics and gynecology: a Baedeker for busy clinicians. Obstet Gynecol Surv 2002;57:S35-S53.
8. Cuzick J, Edwards R, Segman N. Adjusting for non-compliance and contamination in randomized controlled trials. Stat Med 1997;16:1017-1029.
9. Howard G, Chambless LE, Kronmai RA. Assessing differences in clinical trials comparing surgical vs nonsurgical therapy. JAMA 1997;278:1432-1436.
10. Schulz KF, Chalmers I, Grimes DA, Altman DG. Assessing the quality of randomization from reports of controlled trials published in obstetrics and gynecology journals. JAMA 1994;272:225-228.
11. Isemberg SJ, Apt L, Word M. A controlled trial of pivodine-iodine as prophylaxis against ophthalmia neonatorum. N Engl J Med 1995;332:562-566.
12. Schulz KF, Grimes DA. Generation of allocation sequences in randomized trials: chance, not choice. Lancet 2002;359:515-519.
13. Wassertheil-Smoller S. Mostly about clinical trials. In: Wassertheil-Smoller S, ed. Biostatistics and Epidemiology, 2nd ed. New York: Springer-Verlag;1990. pp. 129-146.