Elementos esenciales a considerar en los ensayos de no inferioridad.

Essential elements to consider in non-inferiority studies.

Rolando Uranga 1, Mayelin Mirabal2

1. Centro Nacional Coordinador de Ensayos Clínicos. Calle 23, esq. 200. Reparto Atabey. Playa. Ciudad de La Habana, Cuba. E-mail: rolando@cencec.sld.cu
2. Instituto Finlay. Centro de Investigación-Producción de Vacunas. Ave.27 No. 19805. La Lisa. Ciudad de La Habana, Cuba. E-mail: mmirabal@finlay.edu.cu

RESUMEN

En algunas situaciones es común comparar una vacuna experimental con una vacuna estándar sin pretender mostrar superioridad. La hipótesis nula usual de igualdad es inapropiada y conlleva a dificultades lógicas. Con este artículo se pretende esclarecer la problemática al respecto, revisando la metodología desarrollada para estos efectos y presentando un valor conocido como límite de no inferioridad. Se discuten dos métodos para la realización de una prueba de hipótesis de no inferioridad. Se introducen además dos conceptos útiles en este tipo de estudio: preservación y descuento.

Palabras claves: límite de no inferioridad, diseño de superioridad, preservación, descuento.

In some situations, it is usual to compare an experimental vaccine to a standard one without the objective of showing superiority. The common null hypothesis of equality is inappropriate and leads to logical difficulties. The aim of this work is to clarify some issues about this problem, reviewing the methodology developed for these purposes and presenting a value known as non-inferiority limit. Two methods for conducting a hypothesis test of non-inferiority are discussed and two useful concepts: Preservation and Discounting are also introduced.

Keywords: Non-inferiority limit, superiority design, preservation, discounting.

Texto completo formato PDF

REFERENCIAS

1. William C. Blackwelder. “Proving the null hypothesis” in clinical trials. Controlled Clinical Trials 1982; 3:345-353.
2. Ralph B. D’Agostino, Joseph M. Massaro, and Lisa M. Sullivan Noninferiority trials. Design concepts and issues – the encounters of academic consultants in statistics. Statistics in Medicine 2003; 22:169–186.
3. Tie-Hua Ng. Choice of delta in equivalence testing. Drug Information Journal 2001; 35: 1517-1527.
4. Tie-Hua Ng. A Specification of treatment difference in the design of clinical trials with active controls. Drug Information Journal 1993;27:705-719.
5. Tie-Hua Ng. Active control equivalence studies. Proceedings of the biopharmaceutical section. American Statistical Association 1997; 124-128
6. Tie-Hua Ng. statistical issues in equivalence testing-FDA reviewer’s perspectives. Proceedings of the biopharmaceutical section. American Statistical Association 1999;209-213.
7. Brian L. Wiens. Choosing an equivalence limit for non-inferiority or equivalence studies. Controlled Clinical Trials 2002; 23:2-14.
8. Hauck WW, Anderson S. Some issues in the design and analysis of equivalence trials. Drug Information Journal 1999; 33:109-118.
9. Larry L. Laster, Mary F. Johnson. Non-inferiority trials: the ‘at least as good as’ criterion. Statistics in Medicine 2003; 22:187–200.
10. H. M. James Hung, Jane Wang, Yi Tsong, John Lawrence and Robert T. O’Neil. Some fundamental issues with non-inferiority testing in active controlled trials. Statistics in Medicine 2003; 22:213–225.