Evaluation of multicentre clinical trial data using adaptations of the Mosteller-Tukey procedure.

Two procedures, based on proposals discussed by Mosteller and Tukey, are described for obtaining a combined estimate of the difference between two treatment means and its confidence interval from multicentre clinical trial data. Both procedures provide estimates in the possible presence of heteroscedasticity. The first procedure is designated the primary analysis for efficacy assessment.

Tests for qualitative treatment-by-centre interaction using a 'pushback' procedure.

In multicentre clinical trials using a common protocol, the centres are usually regarded as being a fixed factor, thus allowing any treatment-by-centre interaction to be omitted from the error term for the effect of treatment. However, we feel it necessary to use the treatment-by-centre interaction as the error term if there is substantial evidence that the interaction with centres is qualitative instead of quantitative. To make allowance for the estimated uncertainties of the centre means, we propose choosing a reference value (for example, the median of the ordered array of centre means) and converting the individual centre results into standardized deviations from the reference value.

Developing control charts to review and monitor medication errors.

There is a need to monitor reported medication errors in a hospital setting. Because the quantity of errors vary due to external reporting, quantifying the data is extremely difficult. Typically, these errors are reviewed using classification systems that often have wide variations in the numbers per class per month.

The statistical evaluation of a three-period two-treatment crossover pharmacokinetic drug interaction study.

In a pharmacokinetic drug interaction study, the purpose is to determine whether the coadministration of a drug A with a second drug B alters the absorption/distribution/metabolism/elimination profile of either drug. While the usual design for such studies is a three-period crossover, it cannot be analyzed as such, because the plasma-level data of drug B will be 0 when drug A is given alone, and vice versa. The easiest way to proceed is to do two sets of paired analyses, one on the absorption profile of A (A vs AB), and the other on the absorption profile of B (B vs AB).

Testing the statistical certainty of a response to increasing doses of a drug.

Experiments in which the treatments are composed of a series of doses of a compound and a zero dose control are often used in animal toxicity studies. A test procedure is proposed to assess trends in the response variable. The notion of a no-statistical-significance-of-trend (NOSTASOT) dose is introduced, and questions of multiplicity of statistical tests in this context are addressed.