Comparison of statistical models adjusting for baseline in the analysis of parallel-group thorough QT/QTc studies.

The ICH E14 guidance recommends the use of a time-matched baseline, while others recommend alternative baseline definitions including a day-averaged baseline. In this article we consider six models adjusting for baselines. We derive the explicit covariances and compare their power under various conditions. Simulation results are provided. We conclude that type I error rates are controlled. However, one model outperforms the others on statistical power under certain conditions. In general, the analysis of covariance (ANCOVA) model using a day-averaged baseline is preferred. If the time-matched baseline has to be used as per requests from regulatory agencies, the analysis by time point using ANCOVA model should be recommended.

Sample size calculation for thorough QT/QTc study considering various factors related to multiple time points.

The sample size requirement in a thorough QT/QTc study is discussed under a balanced parallel or crossover study design. First, we explore the impacts of various factors on the study power, including the mean effect profile across time and correlation among time points. Then we estimate the variability parameters needed based on multiple historical studies. Different baseline usage is illustrated to have a significant impact on the analysis variability in the parallel studies. Finally, the sample size calculations and recommendations are given for demonstrating a "negative" drug effect and the study assay sensitivity, respectively.

Use of the average baseline versus the time-matched baseline in parallel group thorough QT/QTc studies.

Using historical studies, we compared the impact of using the average baseline or time-matched baseline on diurnal effect correction, treatment effect estimation, and analysis of variance/covariance (ANOVA/ANCOVA) efficiency in a parallel thorough QT/QTc (TQT) study. Under a multivariate normal distribution assumption, we derived conditions for achieving unbiasness and better efficiency when using the average baseline, and confirmed these conditions using historical TQT studies. Furthermore, simulations were conducted under the randomized trial with and without observed imbalanced baseline settings. We conclude that the analyses using average baseline yield better efficiency and unbiased or less biased results under our TQT study conditions.

Statistical methods for assessing long-term analyte stability in biological matrices.

The objective of a long-term stability experiment is to confirm analyte stability in a given biological matrix, encompassing the duration of time from sample collection to sample analysis for a clinical or preclinical study. While long-term analyte stability has been identified as a key component of bioanalytical method validation, current regulatory guidance provides no specific recommendations regarding the design and analysis of such experiments. This paper reviews and evaluates various experimental designs, data analysis methods, and acceptance criteria for the assessment of long-term analyte stability. Statistical equivalence tests based on linear regression techniques are advocated. Both a nested errors and bivariate mixed model regression approach are suitable for application to long-term stability assessment, and control the risk of falsely concluding stability.

A total error approach for the validation of quantitative analytical methods.

PURPOSE: Typical acceptance criteria for analytical methods are not chosen with regard to the concept of method suitability and are commonly based on ad-hoc rules. Such approaches yield unknown and uncontrolled risks of accepting unsuitable analytical methods and rejecting suitable analytical methods. This paper proposes a formal statistical framework for the validation of analytical methods, which incorporates the use of total error and controls the risks of incorrect decision-making. MATERIALS AND METHODS: A total error approach for method validation based on the use of two-sided beta-content tolerance intervals is proposed. The performance of the proposed approach is compared to the performance of current ad-hoc approaches via simulation techniques. RESULTS: The current ad-hoc approaches for method validation fail to control the risk of incorrectly accepting unsuitable analytical methods. The proposed total error approach controls the risk of incorrectly accepting unsuitable analytical methods and provides adequate power to accept truly suitable methods. CONCLUSION: Current ad-hoc approaches to method validation are inconsistent with ensuring method suitability. A total error approach based on the use of two-sided beta-content tolerance intervals was developed. The total error approach offers a formal statistical framework for assessing analytical method performance. The approach is consistent with the concept of method suitability and controls the risk of incorrectly accepting unsuitable analytical methods.

New confidence bounds for QT studies.

The proposed guidelines for the assessment of the effect of new pharmaceutical agents on the QT interval (beginning of QRS complex to end of T wave on the electrocardiogram) are based on the maximum of a series over time of simple one-sided 95 per cent upper confidence bounds. This procedure is typically very conservative as a procedure for obtaining a 95 per cent bound for the maximum of the population parameters. This paper proposes new bounds for the maximum, both analytical and bootstrap-based, that are lower but still achieve correct coverage in the context of crossover and parallel designs for the most realistic portions of the parameter space.

Two-sided tolerance intervals for balanced and unbalanced random effects models.

A procedure for constructing two-sided beta-content, gamma-confidence tolerance intervals is proposed for general random effects models, in both balanced and unbalanced data scenarios. The proposed intervals are based on the concept of effective sample size and modified large sample methods for constructing confidence bounds on functions of variance components. The performance of the proposed intervals is evaluated via simulation techniques. The results indicate that the proposed intervals generally maintain the nominal confidence and content levels. Application of the proposed procedure is illustrated with a one-fold nested design used to evaluate the performance of a quantitative bioanalytical method.