An Empirical and Simulated Comparison of Some Tests for Detecting Progressiveness of Response with Increasing Doses of a Compound

Abstract

summaryExperiments consisting of several doses of a test agent and a zero dose control are often conducted to evaluate the effect of a compound on the response of interest.et al. (1985) proposed a trend test procedure which uses the minimum pvalue from three candidate dose scalings as a sensitive means for detecting a trend in response with increasing dose. Trend is defined here as a progressiveness, either increasing or decreasing, in response with increasing dose of the test agent. In this paper, we take a closer look at the procedure's inflated type I error rate and propose an adjustment based on the multivariate tdistribution which preserves the nominal significance level.Application of the adjusted trend test to a number of real data sets indicates that its performance is similar to that observed with Bartholomew's and Williams' tests. An evaluation of these three tests also was conducted on simulated data using an apparently novel approach which takes into account the underlying dosage regimen to generate the alternative hypotheses for a broad range of dose response relations. The simulation results indicates that the adjusted trend test is overall more powerful than its two competitors, although there are circumstances where each procedure appears superior. This broad-based power exhibited in both real and simulated settings makes the adjusted trend test an attractive approach.

Histomorphometric assessment of the long-term effects of alendronate on bone quality and remodeling in patients with osteoporosis.

“…For the primary endpoint (assessment of mineralization) a two-sided trend test (18,19) was used to evaluate differences among the treatment groups within each of the osteoporosis studies at a particular timepoint.…”

Adjusted Regression Trend Test for a Multicenter Clinical Trial

“…Similar to Capizzi et al (1992), we consider the following expected mean response at each center and each dose level:…”

“…Tukey, Ciminera, and Heyse (1985) proposed a regressionbased procedure for assessing a trend in response with increasing dose of a compound and for comparing each dose with the control in a stepwise fashion in a one-way design. Capizzi et al (1992) suggested an adjusted trend test procedure that controlled the inflated Type I error observed with the Tukey et al (1985) approach. In this paper, we propose an extension of the adjusted trend test that is suitable for multicenter clinical trials and has less restrictive assumptions than existing approaches.…”

Multiplicity adjustment for multiple endpoints in clinical trials with multiple doses of an active treatment

“…The actions which should be taken by various procedures are as in the table. Procedure (3 ) of both versions reject more hypotheses than Procedures (1 ) and (2 ). The regular Bonferroni procedure rejects H 11 , and the regular Hochberg procedures rejects H 11 and H 21 .…”

“…A well designed closed testing procedure has been shown to have much more power than the traditional Bonferroni procedure. For a trial with the primary objective to assess the dose-response relationship of multiple doses of an active treatment versus a placebo control on one primary endpoint, the stepdown trend tests [1][2][3][4] are natural closed testing procedures for comparing each dose to the placebo control. These stepdown trend test procedures assume an ordered restriction on the mean responses according to the dose levels.…”