Resampling‐based stepwise multiple testing procedures with applications to clinical trial data

2020 ◽  
Author(s):  
Jiwei He ◽  
Feng Li ◽  
Yan Gao ◽  
Mark Rothmann
2019 ◽  
Vol 14 (3) ◽  
pp. 160-172 ◽  
Author(s):  
Aynaz Nourani ◽  
Haleh Ayatollahi ◽  
Masoud Solaymani Dodaran

Background:Data management is an important, complex and multidimensional process in clinical trials. The execution of this process is very difficult and expensive without the use of information technology. A clinical data management system is software that is vastly used for managing the data generated in clinical trials. The objective of this study was to review the technical features of clinical trial data management systems.Methods:Related articles were identified by searching databases, such as Web of Science, Scopus, Science Direct, ProQuest, Ovid and PubMed. All of the research papers related to clinical data management systems which were published between 2007 and 2017 (n=19) were included in the study.Results:Most of the clinical data management systems were web-based systems developed based on the needs of a specific clinical trial in the shortest possible time. The SQL Server and MySQL databases were used in the development of the systems. These systems did not fully support the process of clinical data management. In addition, most of the systems lacked flexibility and extensibility for system development.Conclusion:It seems that most of the systems used in the research centers were weak in terms of supporting the process of data management and managing clinical trial's workflow. Therefore, more attention should be paid to design a more complete, usable, and high quality data management system for clinical trials. More studies are suggested to identify the features of the successful systems used in clinical trials.


Author(s):  
Damian Clarke ◽  
Joseph P. Romano ◽  
Michael Wolf

When considering multiple-hypothesis tests simultaneously, standard statistical techniques will lead to overrejection of null hypotheses unless the multiplicity of the testing framework is explicitly considered. In this article, we discuss the Romano–Wolf multiple-hypothesis correction and document its implementation in Stata. The Romano–Wolf correction (asymptotically) controls the familywise error rate, that is, the probability of rejecting at least one true null hypothesis among a family of hypotheses under test. This correction is considerably more powerful than earlier multiple-testing procedures, such as the Bonferroni and Holm corrections, given that it takes into account the dependence structure of the test statistics by resampling from the original data. We describe a command, rwolf, that implements this correction and provide several examples based on a wide range of models. We document and discuss the performance gains from using rwolf over other multiple-testing procedures that control the familywise error rate.


Sign in / Sign up

Export Citation Format

Share Document