Detecting dose response with contrasts

Analyses of dose response studies should separate the question of the exist ence of a dose response relationship from questions of functional form and finding the optimal dose. A well-chosen contrast among the estimated effect s of the studied doses can make a powerful test for detecting the existence of a dose response relationship. A contrast-based test attains its greates t power when the pattern of the coefficients has the same shape as the true dose response relationship. However, it loses power when the contrast shap e and the true dose response shape are not similar. Thus, a primary test ba sed on a single contrast is often risky. Two (or more) appropriately chosen contrasts can assure sufficient power to justify the cost of a multiplicit y adjustment. An example shows the success of a two-contrast procedure in d etecting dose response, which had frustrated several standard procedures. C opyright (C) 2000 John Wiley & Sons, Ltd.