External Email - Use Caution Hi,
It's possible to analyse longitudinal designs with PALM. Some mild assumptions must hold, and those assumptions are different than those of an LME model. PALM doesn't assume normality, doesn't require a specified form for the dependence structure, but requires compound symmetry. PALM allows non-parametric correction of FWER and is not based on numerical optimization, so it doesn't suffer from convergence failures. On the other hand, LME allows multiple variance components and can accommodate some rather unwieldy designs, but it does make distributional and covariance assumptions and offers no trivial method (other than perhaps FDR) to deal with the multiple testing problem. It's up to you really... All the best, Anderson On Mon, 29 Jul 2019 at 17:00, Greve, Douglas N.,Ph.D. < [email protected]> wrote: > I'm not sure that is a way to do this as it is quite tricky managing the > exchangeability in longitudinal data. Maybe PALM can do it. I'm cc'ing > Anderson in case he wants to weigh in. > > On 7/28/19 7:24 PM, Mark Wagshul wrote: > > > > External Email - Use Caution > > > > Doug, > > > > Thanks. Unfortunately, this is only for the GLM, is there an > > equivalent version for the linear mixed model? I haven’t seen one. I > > guess we could figure out how to integrate lme into mri_glmsim, but > > I’m not sure that’s a better use of our time than manually running the > > simulations. Your thoughts? > > > > Thanks for the help. > > > > Mark > > _______________________ > > Mark Wagshul, PhD > > Albert Einstein College of Medicine > > Bronx, NY > > > > Sent from my iPhone > > > > On Jul 28, 2019, at 4:11 PM, Greve, Douglas N.,Ph.D. > > <[email protected] <mailto:[email protected]>> wrote: > > > >> FreeSurfer has its own permutation software > >> *MailScanner has detected a possible fraud attempt from > >> "nam02.safelinks.protection.outlook.com" claiming to be* > >> > https://surfer.nmr.mgh.harvard.edu/fswiki/FsTutorial/MultipleComparisonsV6.0Perm > >> We also have a handy interface to palm > >> *MailScanner has detected a possible fraud attempt from > >> "nam02.safelinks.protection.outlook.com" claiming to be* > >> https://surfer.nmr.mgh.harvard.edu/fswiki/FsPalm > >> > >> On 7/27/2019 9:33 PM, Mark Wagshul wrote: > >>> > >>> External Email - Use Caution > >>> > >>> Great, thanks! > >>> > >>> Mark > >>> _______________________ > >>> Mark Wagshul, PhD > >>> Albert Einstein College of Medicine > >>> Bronx, NY > >>> > >>> Sent from my iPhone > >>> > >>> On Jul 27, 2019, at 2:43 PM, Antonin Skoch <[email protected] > >>> <mailto:[email protected]>> wrote: > >>> > >>>> External Email - Use Caution > >>>> > >>>> Dear Mark, > >>>> > >>>> I would suggest to use PALM instead: > >>>> > >>>> *MailScanner has detected a possible fraud attempt from > >>>> "nam02.safelinks.protection.outlook.com" claiming to be* > >>>> https://fsl.fmrib.ox.ac.uk/fsl/fslwiki/PALM/UserGuide < > https://nam02.safelinks.protection.outlook.com/?url=https%3A%2F%2Ffsl.fmrib.ox.ac.uk%2Ffsl%2Ffslwiki%2FPALM%2FUserGuide&data=02%7C01%7Cmark.wagshul%40einstein.yu.edu%7Ca32b0472033a420f1ea508d71397c21a%7C04c70eb48f2648079934e02e89266ad0%7C1%7C0%7C636999414844352500&sdata=wODbvJGuGHP8dlfhO4tJjX8Ype0ph%2FbXrjMkTsGFfD8%3D&reserved=0 > > > >>>> > >>>> PALM supports surface-based data. Each vertex has different area, > which has to be accounted when the cluster size is computed. > >>>> > >>>> Antonin Skoch > >>>> > >>>> > >>>> > >>>> Dear Freesurfer experts, > >>>> Hi. We are analyzing cortical thickness data in Freesurfer, > longitudinal data > >>>> in 55 subjects using the linear mixed effects package. We are > finding a number > >>>> of siginificant clusters, and would like to correct for multiple > comparisons > >>>> with permutation testing. We have already run about 2000 > permutations, and > >>>> would like to use TFCE available in randomise rather than empirical > methods to > >>>> set parameters such as the cluster forming threshold. > >>>> > >>>> So, the simple question is, how do we convert our FS format data > (these are F > >>>> statistics at each vertex) into a format which can be read into > randomise? > >>>> > >>>> Thanks for any advice you can provide. > >>>> > >>>> Best, > >>>> > >>>> Mark > >>>> _______________________________________________ > >>>> Freesurfer mailing list > >>>> [email protected] <mailto:[email protected] > > > >>>> > https://nam02.safelinks.protection.outlook.com/?url=https%3A%2F%2Fmail.nmr.mgh.harvard.edu%2Fmailman%2Flistinfo%2Ffreesurfer&data=02%7C01%7Cmark.wagshul%40einstein.yu.edu%7Cb7ea74f6c51b44fac3a508d712c25393%7C04c70eb48f2648079934e02e89266ad0%7C1%7C0%7C636998498148426272&sdata=hwa50qaC%2FS3Ma1o%2Bwy20l99PJ3mInnB%2FJqcX192PWvY%3D&reserved=0 > >>>> < > https://nam02.safelinks.protection.outlook.com/?url=https%3A%2F%2Fmail.nmr.mgh.harvard.edu%2Fmailman%2Flistinfo%2Ffreesurfer&data=02%7C01%7Cmark.wagshul%40einstein.yu.edu%7Ca32b0472033a420f1ea508d71397c21a%7C04c70eb48f2648079934e02e89266ad0%7C1%7C0%7C636999414844362494&sdata=eoEproOAVUGqZFzJhjp47oUBmmjlqxOQstUL7mzs0d0%3D&reserved=0 > > > >>> > >>> _______________________________________________ > >>> Freesurfer mailing list > >>> [email protected] > >>> *MailScanner has detected a possible fraud attempt from > >>> "nam02.safelinks.protection.outlook.com" claiming to be* > >>> https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer > >> > >> _______________________________________________ > >> Freesurfer mailing list > >> [email protected] <mailto:[email protected]> > >> > https://nam02.safelinks.protection.outlook.com/?url=https%3A%2F%2Fmail.nmr.mgh.harvard.edu%2Fmailman%2Flistinfo%2Ffreesurfer&data=02%7C01%7Cmark.wagshul%40einstein.yu.edu%7Ca32b0472033a420f1ea508d71397c21a%7C04c70eb48f2648079934e02e89266ad0%7C1%7C0%7C636999414844382483&sdata=kgZ%2Fj6%2BWbJxmAXz4mpdm6Z%2FZ2UHnnDSEswsPkGTFaVI%3D&reserved=0 > > > > _______________________________________________ > > Freesurfer mailing list > > [email protected] > > https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer > > > > The information in this e-mail is intended only for the person to whom it > is > addressed. If you believe this e-mail was sent to you in error and the > e-mail > contains patient information, please contact the Partners Compliance > HelpLine at > http://www.partners.org/complianceline . If the e-mail was sent to you in > error > but does not contain patient information, please contact the sender and > properly > dispose of the e-mail. > >
_______________________________________________ Freesurfer mailing list [email protected] https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer
