Premium
Providing evidence of efficacy for a new drug
Author(s) -
Ruberg Stephen,
Cairns Victoria
Publication year - 1998
Publication title -
statistics in medicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.996
H-Index - 183
eISSN - 1097-0258
pISSN - 0277-6715
DOI - 10.1002/(sici)1097-0258(19980815/30)17:15/16<1813::aid-sim983>3.0.co;2-8
Subject(s) - test (biology) , efficacy , selection (genetic algorithm) , computer science , drug trial , a priori and a posteriori , control (management) , variable (mathematics) , medicine , clinical trial , econometrics , psychology , drug , risk analysis (engineering) , mathematics , artificial intelligence , epistemology , pharmacology , paleontology , philosophy , pathology , biology , mathematical analysis
There are many issues to consider when designing an efficacy package for drug registration. Generally in Europe and the United States, two or more confirmatory trials demonstrating efficacy ( p <0·025, one‐tailed) of the test treatment versus a suitable control group must be conducted with a priori definition of a primary efficacy endpoint. Exceptions are possible, and there is always extensive discussion whenever less is proposed or more is required. Every aspect of the basic requirement can be questioned: number of trials; choice of control group; selection of primary efficacy variable(s); levels of significance; one‐tailed versus two‐tailed test. These issues will be discussed, and justification is given when proposals are made for deviations from standard practice. Differences between Europe and the U.S. are discussed for certain disease entities. Because the assessment of the weight of evidence in favour of a drug effect is difficult to quantitate, if not impossible, no definitive guidance can be given that is suitable for all circumstances and countries © 1998 John Wiley & Sons, Ltd.