Adaptive Design Methods in Clinical Trials (Biostatistics) by Shein-Chung Chow, Mark Chang

By Shein-Chung Chow, Mark Chang

Even supposing adaptive layout equipment are versatile and worthy in scientific study, very little regulatory instructions can be found. one of many first books at the subject, Adaptive layout tools in scientific Trials provides the rules and methodologies in adaptive layout and research that pertain to diversifications made to trial or statistical systems which are in keeping with accumulated information of ongoing scientific trials. The publication additionally bargains a well-balanced precis of present regulatory views and lately constructed statistical tools during this quarter. After an creation to uncomplicated thoughts and statistical issues of adaptive layout tools, the booklet questions the influence on track sufferer populations because the results of protocol amendments and discusses the generalization of statistical inference. The authors additionally current numerous adaptive layout equipment, together with the place hypotheses are converted in the course of the behavior of medical trials, for dose choice, and frequent adaptive staff sequential layout equipment in scientific trials. Following a dialogue of blind strategies for pattern measurement re-estimation, the booklet describes statistical checks for seamless section II/III adaptive designs and statistical inference for switching adaptively from one remedy to a different. The e-book concludes with machine simulations and numerous case reviews of scientific trials.By delivering theoretical and machine simulation effects, process comparisons, and sensible directions for selecting an optimum layout, Adaptive layout tools in medical Trials fills the necessity for a unified, complete, and up to date source within the scientific study and improvement of adaptive layout and research.

Show description

Read Online or Download Adaptive Design Methods in Clinical Trials (Biostatistics) PDF

Best biostatistics books

Advances in Ranking and Selection, Multiple Comparisons, and Reliability

"S. Panchapakesan has made major contributions to rating and choice and has released in lots of different parts of facts, together with order facts, reliability conception, stochastic inequalities, and inference. Written in his honor, the twenty invited articles during this quantity mirror fresh advances in those fields and shape a tribute to Panchapakesan's effect and effect on those components.

Variation in the Human Genome (Novartis Foundation Symposia)

The mapping of human genes is continuing swiftly. Genes linked to particular inherited illnesses are being pointed out, frequently delivering perception into the molecular explanation for the sickness. in the intervening time, despite the fact that, little attention is being given to the adaptation found in diverse human populations.

Quasi-Least Squares Regression

Drawing at the authors' colossal services in modeling longitudinal and clustered info, Quasi-Least Squares Regression offers a radical therapy of quasi-least squares (QLS) regression-a computational process for the estimation of correlation parameters in the framework of generalized estimating equations (GEEs).

Practical Guide to Clinical Computing Systems, Second Edition: Design, Operations, and Infrastructure

Even supposing informatics trainees and practitioners who think operational computing roles of their association can have quite complex knowing of theoretical informatics, many are unusual with the sensible themes - resembling downtime strategies, interface engines, consumer aid, JCAHO compliance, and budgets - with a view to develop into the mainstay in their operating lives.

Extra info for Adaptive Design Methods in Clinical Trials (Biostatistics)

Sample text

It is desirable to combine phase II and III so that the data can be used more efficiently and duration of the drug development can be reduced. , 2006). , 2006). Bauser and Kieser (1999) provide a two-stage method for this purpose, where the investigators can terminate the trial entirely or drop a subset of regimens for lack of efficacy after the first stage. As pointed out by Sampson and Sill (2005), their procedure is highly flexible, and the distributional assumptions are kept to a minimum. This results in a usual design in a number of settings.

We will refer to such a patient population as the actual patient population under study. After a given protocol amendment, we denote the actual patient population by (µ1 , σ1 ), where µ1 = µ+ε is the population mean of the primary study endpoint and σ1 = Cσ (C > 0) denotes the population standard deviation of the primary study endpoint. In this chapter, we will refer to ε and C as the shift and scale parameters of the target patient population (µ, σ ) after modification is made. As it can be seen, the difference between the actual patient population (µ1 , σ1 ) and the original target patient population (µ, σ ) can be characterized as follows: µ1 µ µ+ε ∆µ = , = = |∆| σ1 Cσ σ σ where 1 + ε/µ C is a measure of change in the signal-to-noise ratio of the actual patient population as compared to the original target population.

In practice, it is a concern that a major (or significant) adaptation could result in a totally different patient population. During the conduct of a clinical trial, if adaptations are made frequently, the target patient population is in fact a moving target patient population (Chow, Chang, and Pong, 2005). As a result, it is difficult to draw an accurate and reliable statistical inference on the moving target patient population. Thus, in practice, it is of interest to determine the impact of adaptive design methods on the target patient population and consequently the corresponding statistical inference and power analysis for sample size calculation.

Download PDF sample

Rated 4.40 of 5 – based on 17 votes