Document Detail

Detecting data fabrication in clinical trials from cluster analysis perspective.
MedLine Citation:
PMID:  20936626     Owner:  NLM     Status:  MEDLINE    
Detecting data fabrication is of great importance in clinical trials. As the role of statisticians in detecting abnormal data patterns has grown, a large number of statistical procedures have been developed, most of which are based on descriptive statistics. Based upon the fact that substantial data fabrication cases have certain clustering structures, this paper discusses the potential for the use of statistical clustering method in fraud detection. Three clustering patterns, angular, neighborhood and repeated measurements clustering, are identified and explored. Correspondingly, simple and efficient test statistics are proposed and randomization tests are carried out. The proposed methods are applied to a 12-week multi-center study for illustration. Extensive simulations are conducted to validate the effectiveness of the procedures.
Xiaoru Wu; Martin Carlsson
Related Documents :
7701156 - Detection and assessment of clusters of disease: an application to nuclear power plant ...
16161806 - Applications of binary segmentation to the estimation of quantal response curves and sp...
16156936 - Mixture modeling with pairwise, instance-level class constraints.
85246 - A detection algorithm for multiform premature ventricular contractions.
21489426 - Withdrawn: neural crest-dependent bmp signaling directs the timing of mandibular osteog...
21428506 - Extension of deconvolution algorithms for the mapping of moving acoustic sources.
Publication Detail:
Type:  Journal Article     Date:  2010-10-08
Journal Detail:
Title:  Pharmaceutical statistics     Volume:  10     ISSN:  1539-1612     ISO Abbreviation:  Pharm Stat     Publication Date:    2011 May-Jun
Date Detail:
Created Date:  2011-05-16     Completed Date:  2012-01-12     Revised Date:  2012-01-30    
Medline Journal Info:
Nlm Unique ID:  101201192     Medline TA:  Pharm Stat     Country:  England    
Other Details:
Languages:  eng     Pagination:  257-64     Citation Subset:  IM    
Copyright Information:
Copyright © 2010 John Wiley & Sons, Ltd.
Department of Statistics, Columbia University, New York, USA.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Clinical Trials as Topic / statistics & numerical data*
Cluster Analysis*
Computer Simulation*
Fraud / statistics & numerical data
Models, Statistical*
Models, Theoretical
Monte Carlo Method
Random Allocation
Reproducibility of Results
Research Design

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Previous Document:  The role of the minimum clinically important difference and its impact on designing a trial.
Next Document:  Anomalous stoichiometry, layered structure, and magnetic ordering for the Prussian blue analogue [NE...