Dealing with excess of zeros in the statistical analysis of magnetic resonance imaging lesion count in multiple sclerosis

被引：7

作者：

Francois, Mercier ^{[1
]}

Peter, Chin ^{[2
]}

Gordon, Francis ^{[2
]}

机构：

[1] Pharsight Consulting Serv, St Louis, MO USA

[2] Novartis Pharmaceut, Neuroinflammat Clin Sci Unit, E Hanover, NJ USA

来源：

PHARMACEUTICAL STATISTICS | 2012年 / 11卷 / 05期

关键词：

negative binomial; zero inflation; count; brain lesion; generalized linear mixed-effect model; multiple sclerosis; fingolimod; INFLATED POISSON REGRESSION; NEGATIVE BINOMIAL MODEL; CLINICAL-TRIALS; GADOLINIUM-ENHANCEMENT; HURDLE MODELS; SCORE TESTS; FINGOLIMOD; DISABILITY; LIKELIHOOD;

D O I：

10.1002/pst.1529

中图分类号：

R9 [药学];

学科分类号：

1007 ;

摘要：

Lesion count observed on brain magnetic resonance imaging scan is a common end point in phase?2 clinical trials evaluating therapeutic treatment in relapsing remitting multiple sclerosis (MS). This paper compares the performances of Poisson, zero-inflated poisson (ZIP), negative binomial (NB), and zero-inflated NB (ZINB) mixed-effects regression models in fitting lesion count data in a clinical trial evaluating the efficacy and safety of fingolimod in comparison with placebo, in MS. The NB and ZINB models prove to be superior to the Poisson and ZIP models. We discuss the advantages and limitations of zero-inflated models in the context of MS treatment. Copyright (C) 2012 John Wiley & Sons, Ltd.

引用

页码：417 / 424

页数：8

共 43 条

[1] A longitudinal model for magnetic resonance imaging lesion count data in multiple sclerosis patients [J].