A review of uniform cross-over designs

Uniform cross-over designs form an important family of experimental designs. They have been applied in many scientific disciplines including clinical trials, agricultural studies and psychological experiments. In this paper we consider the four types of uniform cross-over design, as given by Williams [1949. Experimental designs balanced for the estimation of residual effects of treatments. Aust. J. Sci. Res. 2, 149–168], Cheng and Wu [1980. Balanced repeated measurements designs. Ann. Statist. 8, 1272–1283. Corrigendum 11 (1983) 349], Bate and Jones [2006. The construction of nearly balanced and nearly strongly balanced uniform cross-over designs. J. Statist. Plann. Inference 136, 3248–3267] and Kunert [1983. Optimal design and refinement of the linear model with applications to repeated measurements designs. Ann. Statist. 11, 247–257]. The efficiency of these designs, existence criteria and methods of construction are described.     

Viewpoint: observations on scaled average bioequivalence

The two one-sided test procedure (TOST) has been used for average bioequivalence testing since 1992 and is required when marketing new formulations of an approved drug. TOST is known to require comparatively large numbers of subjects to demonstrate bioequivalence for highly variable drugs, defined as those drugs having intra-subject coefficients of variation greater than 30%. However, TOST has been shown to protect public health when multiple generic formulations enter the marketplace following patent expiration. Recently, scaled average bioequivalence (SABE) has been proposed as an alternative statistical analysis procedure for such products by multiple regulatory agencies. SABE testing requires that a three-period partial replicate cross-over or full replicate cross-over design be used. Following a brief summary of SABE analysis methods applied to existing data, we will consider three statistical ramifications of the proposed additional decision rules and the potential impact of implementation of scaled average bioequivalence in the marketplace using simulation. It is found that a constraint being applied is biased, that bias may also result from the common problem of missing data and that the SABE methods allow for much greater changes in exposure when generic-generic switching occurs in the marketplace.     

A Bayesian approach to the statistical analysis of device preference studies

Drug delivery devices are required to have excellent technical specifications to deliver drugs accurately, and in addition, the devices should provide a satisfactory experience to patients because this can have a direct effect on drug compliance. To compare patients' experience with two devices, cross-over studies with patient-reported outcomes (PRO) as response variables are often used. Because of the strength of cross-over designs, each subject can directly compare the two devices by using the PRO variables, and variables indicating preference (preferring A, preferring B, or no preference) can be easily derived. Traditionally, methods based on frequentist statistics can be used to analyze such preference data, but there are some limitations for the frequentist methods. Recently, Bayesian methods are considered an acceptable method by the US Food and Drug Administration to design and analyze device studies. In this paper, we propose a Bayesian statistical method to analyze the data from preference trials. We demonstrate that the new Bayesian estimator enjoys some optimal properties versus the frequentist estimator.     

Design of human immunodeficiency virus intervention trials in developing countries

Randomized controlled trials are recognized as the 'gold standard' for evaluating the effect of health interventions, yet few such trials of human immunodeficiency virus (HIV) preventive interventions have been conducted. We discuss the role of randomized trials in the evaluation of such interventions, and we review the strengths and weaknesses of this and other approaches. Randomization of clusters (groups of individuals) may sometimes be appropriate, and we discuss several issues in the design of such cluster-randomized trials, including sample size, the definition and size of clusters, matching and the role of base-line data. Finally we review some general issues in the design of HIV prevention trials, including the choice of the study population, trial end points and ethical issues. It is argued that randomized trials have an important role to play in the evolution of HIV control.     

A RANDOMIZED LONGITUDINAL PLAY-THE-WINNER DESIGN FOR REPEATED BINARY DATA

In some clinical trials with two treatment arms, the patients enter the study at different times and are then allocated to one of two treatment groups. It is important for ethical reasons that there is greater probability of allocating a patient to the group that has displayed more favourable responses up to the patient's entry time. There are many adaptive designs in the literature to meet this ethical constraint, but most have a single binary response. Often the binary response is longitudinal in nature, being observed repeatedly over different monitoring times. This paper develops a randomized longitudinal play‐the‐winner design for such binary responses which meets the ethical constraint. Some performance characteristics of this design have been studied. It has been implemented in a trial of pulsed electro‐magnetic field therapy with rheumatoid arthritis patients.     

TITE‐BOIN‐ET: Time‐to‐event Bayesian optimal interval design to accelerate dose‐finding based on both efficacy and toxicity outcomes

One of the primary purposes of an oncology dose‐finding trial is to identify an optimal dose (OD) that is both tolerable and has an indication of therapeutic benefit for subjects in subsequent clinical trials. In addition, it is quite important to accelerate early stage trials to shorten the entire period of drug development. However, it is often challenging to make adaptive decisions of dose escalation and de‐escalation in a timely manner because of the fast accrual rate, the difference of outcome evaluation periods for efficacy and toxicity and the late‐onset outcomes. To solve these issues, we propose the time‐to‐event Bayesian optimal interval design to accelerate dose‐finding based on cumulative and pending data of both efficacy and toxicity. The new design, named “TITE‐BOIN‐ET” design, is nonparametric and a model‐assisted design. Thus, it is robust, much simpler, and easier to implement in actual oncology dose‐finding trials compared with the model‐based approaches. These characteristics are quite useful from a practical point of view. A simulation study shows that the TITE‐BOIN‐ET design has advantages compared with the model‐based approaches in both the percentage of correct OD selection and the average number of patients allocated to the ODs across a variety of realistic settings. In addition, the TITE‐BOIN‐ET design significantly shortens the trial duration compared with the designs without sequential enrollment and therefore has the potential to accelerate early stage dose‐finding trials.     

Sample Size Calculation and Blinded Sample Size Recalculation in Clinical Trials Where the Treatment Effect is Measured by the Relative Risk

In clinical trials with binary endpoints, the required sample size does not depend only on the specified type I error rate, the desired power and the treatment effect but also on the overall event rate which, however, is usually uncertain. The internal pilot study design has been proposed to overcome this difficulty. Here, nuisance parameters required for sample size calculation are re-estimated during the ongoing trial and the sample size is recalculated accordingly. We performed extensive simulation studies to investigate the characteristics of the internal pilot study design for two-group superiority trials where the treatment effect is captured by the relative risk. As the performance of the sample size recalculation procedure crucially depends on the accuracy of the applied sample size formula, we firstly explored the precision of three approximate sample size formulae proposed in the literature for this situation. It turned out that the unequal variance asymptotic normal formula outperforms the other two, especially in case of unbalanced sample size allocation. Using this formula for sample size recalculation in the internal pilot study design assures that the desired power is achieved even if the overall rate is mis-specified in the planning phase. The maximum inflation of the type I error rate observed for the internal pilot study design is small and lies below the maximum excess that occurred for the fixed sample size design.     

Analysis of cross-over designs via growth curve models

Models for repeated measures cross-over designs are defined in terms of growth curve models. In the paper two specific cross-over designs, called the AB:BA and ABAB:BABA design, are studied. The maximum-likelihood (ML) estimators for the parameters are derived by utilizing the theory for growth curve models. A model with a structured dispersion matrix is defined for the AB:BA design, and a specific linear transformation is used to derive estimators in a convenient way. To illustrate numerically, ML estimates are calculated for an ABAB:BABA study.     

Robustness and monotonicity properties of generalized correlation coefficients

A new class of generalized correlation coefficients that contains the Pearson and Kendall statistics as special cases was defined by Chinchilli et al. (2005) and applied to the estimation of correlations coefficients within the context of 2×2 cross-over designs for clinical trials. In this paper, we determine the infinitesimal robustness and local stability properties of these generalized correlation coefficients by deriving their corresponding influence functions. For cases in which the population distribution is a bivariate normal or a mixture of bivariate normal distributions we obtain explicit formulas, and establish monotonicity and sign-reverse rule properties of the generalized correlation coefficients.     

Cross-over Designs in the Presence of Higher Order Carry-overs

In cross-over experiments, where different treatments are applied successively to the same experimental unit over a number of time periods, it is often expected that a treatment has a carry-over effect in one or more periods following its period of application. The effect of interaction between the treatments in the successive periods may also affect the response. However, it seems that all systematic studies of the optimality properties of cross-over designs have been done under models where carry-over effects are assumed to persist for only one subsequent period. This paper proposes a model which allows for the possible presence of carry-over effects up to k subsequent periods, together with all the interactions between treatments applied at k + 1 successive periods. This model allows the practitioner to choose k for any experiment according to the requirements of that particular experiment. Under this model, the cross-over designs are studied and the class of optimal designs is obtained. A method of constructing these optimal designs is also given.     

A clinical application of expert system methodology

In recent years, several expert systems have been developed for practical applications in applied statistical methodologies. Existing expert systems in statistics have explored several areas, e.g. the determination of appropriate statistical tests, regression analysis, and determination of the ‘best’ experimental design for industrial screening experiments. We present here the DESIGN EXPERT which is a prototype expert system for the design of complex statistical experiments. It is intended for scientific investigators and statisticians who must design and analyze complex experiments, e.g. multilevel medical experiments with nested factors, repeated measures, and both fixed and random eflects. This system is ‘expert’ in the sense that it is capable of the following:(i) recognize specific types of complex experimental designs, based on the application of inference rules to non-technical information supplied by the user; (ii) encode the obtained and inferred information in a flexible general-purpose internal representation, for use by other program modules; (iii) generate analysis of variance tables for the recognized design and an appropriate BMDP runfile for data analysis, using the encoded information. DESIGN EXPERT is capable of recognizing randomized block designs, including lattice designs within embedded Latin squares, cross-over designs, split plots, nesting, repeated measures and covariates. It is written in an experimental programming language developed specifically for research in artificial intelligence.     

Properties of adaptive clinical trial signature design in the presence of gene and gene-treatment interaction

Traditional phase III clinical trials are powered to detect an overall treatment effect. However, it has increasingly been shown that many treatments are effective only for a subset of a population. The adaptive signature design uses genomic/proteomic information to prospectively predict a subset of patients more sensitive to treatment. Tests for overall treatment effect and for treatment effect in the predicted subset are conducted. In this work properties of the adaptive signature design are investigated through simulation. It was found that models which excluded expression main effect terms had higher empirical power than models which included them.     

A nonparametric test for similarity of marginals—With applications to the assessment of population bioequivalence

In this paper we suggest a completely nonparametric test for the assessment of similar marginals of a multivariate distribution function. This test is based on the asymptotic normality of Mallows distance between marginals. It is also shown that the n out of n bootstrap is weakly consistent, thus providing a theoretical justification to the work in Czado, C. and Munk, A. [2001. Bootstrap methods for the nonparametric assessment of population bioequivalence and similarity of distributions. J. Statist. Comput. Simulation 68, 243–280]. The test is extended to cross-over trials and is applied to the problem of population bioequivalence, where two formulations of a drug are shown to be similar up to a tolerable limit. This approach was investigated in small samples using bootstrap techniques in Czado, C., Munk, A. [2001. Bootstrap methods for the nonparametric assessment of population bioequivalence and similarity of distributions. J. Statist. Comput. Simulation 68, 243–280], showing that the bias corrected and accelerated bootstrap yields a very accurate and powerful finite sample correction. A data example is discussed.     

Doubly adaptive biased coin designs with heterogeneous responses

Doubly adaptive biased coin design (DBCD) is an important family of response-adaptive randomization procedures for clinical trials. It uses sequentially updated estimation to skew the allocation probability to favor the treatment that has performed better thus far. An important assumption for the DBCD is the homogeneity assumption for the patient responses. However, this assumption may be violated in many sequential experiments. Here we prove the robustness of the DBCD against certain time trends in patient responses. Strong consistency and asymptotic normality of the design are obtained under some widely satisfied conditions. Also, we propose a general weighted likelihood method to reduce the bias caused by the heterogeneity in the inference after a trial. Some numerical studies are also presented to illustrate the finite sample properties of DBCD.     

Designing historical control studies with survival endpoints using exact statistical inference

Historical control trials compare an experimental treatment with a previously conducted control treatment. By assigning all recruited samples to the experimental arm, historical control trials can better identify promising treatments in early phase trials compared with randomized control trials. Existing designs of historical control trials with survival endpoints are based on asymptotic normal distribution. However, it remains unclear whether the asymptotic distribution of the test statistic is close enough to the true distribution given relatively small sample sizes in early phase trials. In this article, we address this question by introducing an exact design approach for exponentially distributed survival endpoints, and compare it with an asymptotic design in both real examples and simulation examples. Simulation results show that the asymptotic test could lead to bias in the sample size estimation. We conclude the proposed exact design should be used in the design of historical control trials.     

Study design of single‐arm phase II immunotherapy trials with long‐term survivors and random delayed treatment effect

In the traditional study design of a single‐arm phase II cancer clinical trial, the one‐sample log‐rank test has been frequently used. A common practice in sample size calculation is to assume that the event time in the new treatment follows exponential distribution. Such a study design may not be suitable for immunotherapy cancer trials, when both long‐term survivors (or even cured patients from the disease) and delayed treatment effect are present, because exponential distribution is not appropriate to describe such data and consequently could lead to severely underpowered trial. In this research, we proposed a piecewise proportional hazards cure rate model with random delayed treatment effect to design single‐arm phase II immunotherapy cancer trials. To improve test power, we proposed a new weighted one‐sample log‐rank test and provided a sample size calculation formula for designing trials. Our simulation study showed that the proposed log‐rank test performs well and is robust of misspecified weight and the sample size calculation formula also performs well.     

Multivariate analysis for the two-period repeated measures crossover design with application to clinical trials

Multivariate analysis techniques are applied to the two-period repeated measures crossover design. The approach considered in this paper has the advantage over the univariate analysis approach proposed recently by Wallenstein and Fisher (1977) that the former does not require any specific structure on the variance-covariance matrix of the repeated measures factor. (It should be noted that sums and differences of observations over periods are used for all tests. Therefore, there are two matrices under consideration, one for sums and one for differences.) Tests of significance are derived using the Wilks? criterion, and the procedure is illustrated with a numerical example from the area of clinical trials.     

Orthogonal-array composite design for the third-order models

In many industrial trials, the second-order models may not be enough to fit the non linearity of the underlying model, and the third-order models may be considered. In this article, the orthogonal-array composite design (OACD), combined with two-level OA and four-level OA and denoted by OACD₄, is proposed to estimate the second-order and third-order models. It is shown that OACD₄ has good properties and has higher efficiency than other types of designs for the third-order models, and OACD₄ can perform multiple analysis for cross-validation. The usefulness of OACD₄ is also shown by a case study for polymer synthesis experiment.     

Unifying CRM and EWOC designs for phase I cancer clinical trials

The main goal of phase I cancer clinical trials is to determine the highest dose of a new therapy associated with an acceptable level of toxicity for the use in a subsequent phase II trial. The continual reassessment method (CRM) [O’Quigley, J., Pepe, M., Fisher, L., 1990. Continual reassessment method: a practical design for phase I clinical trials in cancer. Biometrics 46, 33–48] and escalation with overdose control (EWOC) [Babb, J., Rogatko, A., Zacks, S., 1998. Cancer phase I clinical trials: efficient dose escalation with overdose control. Statist. Med. 17 (10), 1103–1120] are two model-based designs used for phase I cancer clinical trials. A few modifications of the (original) CRM and EWOC have been made by many authors. In this paper, we show how CRM and EWOC can be unified and present a hybrid design. We study the characteristics of the approach of the hybrid design. The comparisons of the three designs (CRM, EWOC, and the hybrid design) are presented by convergence rates and overdose proportions. The simulation results show that the hybrid design generally has faster convergence rates than EWOC and smaller overdose proportions than CRM, especially when the true maximum tolerated dose (MTD) is above the mid-level of the dose range considered. The performance of these three designs is also evaluated in terms of sensitivity to outliers.     

Life and death decisions

It has recently been suggested 1 that many clinical trials should have a data monitoring and ethics committee, and that on this committee should be a statistician. Such committees are attached to individual trials and are distinct from local ethics committees, which are not required to have a statistician and are not concerned solely with trials. Given the plethora of trials, there will be increasing demand for statisticians to sit on these committees. Although it is both an honour and a privilege, Mike Campbell warns that membership should not be undertaken lightly.