Show simple item record

dc.contributor.authorBOKDE, ARUNen
dc.date.accessioned2015-03-11T12:29:44Z
dc.date.available2015-03-11T12:29:44Z
dc.date.issued2015en
dc.date.submitted2015en
dc.identifier.citationFritsch V, Da Mota B, Loth E, Varoquaux G, Banaschewski T, Barker GJ, Bokde AL, Brühl R, Butzek B, Conrod P, Flor H, Garavan H, Lemaitre H, Mann K, Nees F, Paus T, Schad DJ, Schümann G, Frouin V, Poline JB, Thirion B, Robust regression for large-scale neuroimaging studies., NeuroImage, 111, 2015, 431-441en
dc.identifier.otherYen
dc.identifier.urihttp://hdl.handle.net/2262/73543
dc.descriptionPUBLISHEDen
dc.description.abstractMulti-subject datasets used in neuroimaging group studies have a complex structure, as they exhibit non-stationary statistical properties across regions and display various artifacts. While studies with small sample sizes can rarely be shown to deviate from standard hypotheses (such as the normality of the residuals) due to the poor sensitivity of normality tests with low degrees of freedom, large-scale studies (e.g. >100 subjects) exhibit more obvious deviations from these hypotheses and call for more refined models for statistical inference. Here, we demonstrate the benefits of robust regression as a tool for analyzing large neuroimaging cohorts. First, we use an analytic test based on robust parameter estimates; based on simulations, this procedure is shown to provide an accurate statistical control without resorting to permutations. Second, we show that robust regression yields more detections than standard algorithms using as an example an imaging genetics study with 392 subjects. Third, we show that robust regression can avoid false positives in a large-scale analysis of brain-behavior relationships with over 1500 subjects. Finally we embed robust regression in the Randomized Parcellation Based Inference (RPBI) method and demonstrate that this combination further improves the sensitivity of tests carried out across the whole brain. Altogether, our results show that robust procedures provide important advantages in large-scale neuroimaging group studiesen
dc.description.sponsorshipThis work was supported by Digiteo grants (HiDiNim project No. 2010-42D and ICoGeN project), the ANR grant ANR-10-BLAN-0128, and the Microsoft Inria joint center grant A-brain. This work was supported by the European Union-funded FP6 Integrated Project IMAGEN (Reinforcement-related behavior in normal brain function and psychopathology) (LSHM-CT-2007-037286), the FP7 projects IMAGEMEND and MATRICS and the Innovative Medicine Initiative Project EU-AIMS (115300-2), Medical Research Council Programme Grant “Developmental pathways into adolescent substance abuse” (93558), as well as the Swedish funding agency FORMAS. Further support was provided by the Bundesministerium für Bildung und Forschung (eMED SysAlc; AERIAL; 1EV0711). The authors thank Dr. Danilo Bzdok, Institute of Neuroscience and Medicine (INM-1), Research Center Jülich, Germany, for the valuable suggestions regarding the quality of the manuscript. They also thank the Centre d'Analyse et Traitement des Images (CATI) for giving access to their cluster.en
dc.format.extent431-441en
dc.language.isoenen
dc.relation.ispartofseriesNeuroImageen
dc.relation.ispartofseries111en
dc.rightsYen
dc.subjectrobust regressionen
dc.subject.lcshrobust regressionen
dc.titleRobust regression for large-scale neuroimaging studies.en
dc.typeJournal Articleen
dc.type.supercollectionscholarly_publicationsen
dc.type.supercollectionrefereed_publicationsen
dc.identifier.peoplefinderurlhttp://people.tcd.ie/bokdeaen
dc.identifier.rssinternalid101830en
dc.identifier.doihttp://dx.doi.org/10.1016/j.neuroimage.2015.02.048en
dc.rights.ecaccessrightsopenAccess
dc.subject.TCDThemeNeuroscienceen
dc.identifier.orcid_id0000-0003-0114-4914en


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record