PubMed Health⌕ Search

PubMed · 16422308

Group sequential methods for cluster randomization trials with binary outcomes.

Abstract

BACKGROUND: Cluster randomization trials in which intact social units are randomly assigned to different intervention groups have become very popular in recent years, particularly for the evaluation of innovations in the delivery of health care. An extensive literature dealing with the associated methodological challenges has also appeared. Although the monitoring of such trials using formal stopping rules is clearly indicated when the outcomes are irreversible and individual-level data are available sequentially, simple and reliable statistical methods that may be used for this purpose are currently not available. PURPOSE: To investigate the validity of standard group sequential methods when applied to cluster randomization trials having binary outcomes. METHODS: The large sample distributions for each of five test statistics computed from sequentially accumulated data are derived. A simulation study is performed to evaluate the finite sample properties of these statistics when applied to the interim analysis of cluster randomization trials. Data from the World Health Organization antenatal care trial are used to illustrate the methods. RESULTS: Each of the joint distributions is shown to be characterized by a covariance structure that asymptotically satisfies an independent increments structure, a foundation that simplifies group sequential methods. The simulation study reveals that four of the five test statistics evaluated provide satisfactory performance with as few as 10 clusters allocated to each of two interventions. LIMITATIONS: The applicability of our results to effect estimation following a group sequential cluster randomization trial is not investigated, although a theoretical foundation which may be used for this purpose is presented. CONCLUSIONS: Standard group sequential methods can be applied to cluster randomization trials when interim analyses are warranted.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Guang Yong Zou, Allan Donner, Neil Klar. 2005. Group sequential methods for cluster randomization trials with binary outcomes.. https://doi.org/10.1191/1740774505cn126oa. https://pubmed.health/record/pubmed%3A16422308/group-sequential-methods-for-cluster-randomization-trials-with-binary-outcomes

Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite PubMed Health by Indiciae: BibTeX · RIS.

KEEP EXPLORING

Related citations

On the exact interval estimation for the difference in paired areas under the ROC curves.

An important measure for comparison of accuracy between two diagnostic procedures is the difference in paired areas under the receiver operating characteristic (ROC) curves. Non-parametric and maximum likelihood methods have been proposed for interval estimation for the difference in paired areas under ROC curves. However, these two methods are asymptotic procedures and their performance in finite sample sizes has not been thoroughly investigated. We propose to use the concept of generalized pivotal quantities (GPQs) to construct an exact confidence interval for the difference in paired areas under ROC curves. A simulation study is conducted to empirically investigate the probability coverage and expected length of the three methods for various combinations of sample sizes, values of the area under the ROC curve and correlations. Simulation results demonstrate that the exact confidence interval based on the concept of GPQs provides not only sufficient probability coverage but also reasonable expected length. Numerical examples using published data sets illustrate the proposed method.

Clinical Trials as Topic↗

An efficient test for the analysis of dichotomized variables when the reliability is known.

A difference in an outcome variable between the treatment groups in a trial does not necessarily mean that there is a difference in the number of patients who experience relevant improvement on that variable. When the relevant improvement corresponds with an outcome or change in outcome that exceeds a certain threshold, the outcome variable can be dichotomized. A responder is a patient whose outcome exceeds the threshold. Comparisons can be made between the number of responders in the two treatment groups using logistic regression, or some other method to evaluate binary outcomes. An important disadvantage of this approach is the loss of power. In general, it is more efficient to test the difference between the mean values. We developed a statistical test that compares response rates for a dichotomized variable. It requires that an estimate of the reliability of the outcome variable is available. Simulations showed that the test was valid and robust over a wide range of distributions and sample sizes. The power was greater than the power of a chi(2) test, which would enable substantial reduction in the sample size.

Clinical Trials as Topic↗

Sample size determination for logistic regression revisited.

There is no consensus on the approach to compute the power and sample size with logistic regression. Some authors use the likelihood ratio test; some use the test on proportions; some suggest various approximations to handle the multivariate case. We advocate the use of the Wald test since the Z-score is routinely used for statistical significance testing of regression coefficients. The null-variance formula became popular from early studies, which contradicts modern software, which utilizes the method of maximum likelihood estimation (MLE), when the variance of the MLE is estimated at the MLE, not at the null. We derive general Wald-based power and sample size formulas for logistic regression and then apply them to binary exposure and confounder to obtain a closed-form expression. These formulas are applied to minimize the total sample size in a case-control study to achieve a given power by optimizing the ratio of controls to cases. Approximately, the optimal number of controls to cases is equal to the square root of the alternative odds ratio. Our sample size and power calculations can be carried out online at www.dartmouth.edu/ approximately eugened.

Clinical Trials as Topic↗