A Review of the Performance of Tests used to Establish Whether There is a Drug Effect in Dose-Response Studies
- PDF / 419,855 Bytes
- 10 Pages / 504 x 719.759 pts Page_size
- 98 Downloads / 199 Views
Printed in the USA. All rights reserved.
W2-86 15/98 Copyright 0 1998 Drug Information Association Inc.
A REVIEW OF THE PERFORMANCE OF TESTS USED TO ESTABLISH WHETHER THERE IS A DRUG EFFECT
IN DOSE-RESPONSE STUDIES ALANPHILLIPS, BSc, PHD Wyeth Research United Kingdom, Berkshire, United Kingdom
Within the pharmaceutical industry the assessment of dose-response is a critical part of a drug development program. When analyzing dose-response studies in clinical research one of the most important questions to be addressed is whether there is a drug effect since only once this is established can other analyses be pe8ormed to assess the nature of the dose-response relationship. In this paper thepegormance of eight testsfor establishing a drug effect will be compared for a variety of different patterns of results. It will be shown that specialized tests conditioning on the a priori ordering of responses are robust to a variety of different pattern of results, and therefore, should be used. The more traditional approaches used by statisticians in the pharmaceutical industry based on analysis of variance lead to a loss of powe,: Key Words: Drug effect; Contrast coefficients; Williams’ test; Bartholomew’s test; Jonck-
heere’s test; Simulation
INTRODUCTION WITHIN THE PHARMACEUTICAL industry the assessment of dose-response is a critical part of a drug development program. Dose-response studies are undertaken in pharmacology, toxicology, and clinical research to establish the effectiveness and safety of a new drug, and the information obtained is used to prepare dosage and administration instructions. The most commonly used study design to assess dose-response in clinical research in the pharmaceutical industry is the randomized parallel group study, where patients are
allocated to one of several fixed dose groups. Whenever ethical one of the groups is usually a placebo. The test drug dose levels are often determined by clinical judgement. Patients may be placed immediately on the selected dosage or may require a ‘forced’ titration to it. Qpically, three dose levels are included in each study. A positive control is also sometimes included to establish the ‘sensitivity’ of the study. As discussed by Ruberg (l), in studying the dose-response relationship of a new drug the focus of any analysis is to answer one of the following questions:
1. Is there any drug effect? 2. What doses exhibit a response different from control? Reprint address: Alan Phillips, BSc, PhD, Wyeth Re3. What is the nature of the dose-response search United Kingdom, Huntercornbe Lane South, relationship?, or Taplow, Maidenhead, Berkshire, SL6 OPH, United 4. What is the optimal dose? Kingdom. E-Mail: [email protected]
684
Alan Phillips
Each question becomes increasingly more specific in its quest for information about the bg. As with any clinical trial, in accordance with regulatory guidelines such as the Committee for Proprietary Medicinal Products (CPMP) Biostatistical guidelines (2), when designing dose-response studies it is good statistical pr
Data Loading...
