From Julien.Doyon@UMontreal.CA Thu Nov 8 17:59:36 2001 Received: from ulys.POSTE.UMontreal.CA (ulys.POSTE.UMontreal.CA [132.204.2.41]) by bottom.bic.mni.mcgill.ca (8.11.3/8.11.3) with ESMTP id fA8MxZN15162 for ; Thu, 8 Nov 2001 17:59:36 -0500 (EST) Received: from doyonj-psy.umontreal.ca (doyonj.PSY.UMontreal.CA [132.204.123.94]) by ulys.POSTE.UMontreal.CA (8.11.6/8.11.6) with ESMTP id fA8MxYO3288312 for ; Thu, 8 Nov 2001 17:59:34 -0500 (EST) Message-Id: <5.1.0.14.1.20011108181240.02262028@poste.umontreal.ca> X-Sender: doyonjul@poste.umontreal.ca X-Mailer: QUALCOMM Windows Eudora Version 5.1 Date: Thu, 08 Nov 2001 18:12:54 -0500 To: Kate HANRATTY From: Julien Doyon Subject: Re: t-stat thresholds - single subject analyses In-Reply-To: <20011108171938.A4539@bottom.bic.mni.mcgill.ca> Mime-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1"; format=flowed Content-Transfer-Encoding: 8bit X-MIME-Autoconverted: from quoted-printable to 8bit by bottom.bic.mni.mcgill.ca id fA8MxZN15162 Status: RO Content-Length: 1106 Lines: 45 This is very useful. THanks Julien At 17:19 2001-11-08 -0500, you wrote: >Just a follow up to my discussion with Peter Neelin about this >topic... > >If you analyze data from a single subject, the only way to get a >t-stat image is to do a regression rather than a subtraction (if n=1, >there is no variance!) > >And, if you do regression analysis, the regular thresholds apply >depending on the resel size and size of the search region (see Worsley >et al., '96). > >When comparing one subject to a control group, using regression >technique is still the preferred approach, and the regular thresholds >apply. > >Hope this is useful, >Kate. > >-- >Kate Hanratty Tel 343-6111 xt 4615 >Dep. de psychologie, U. de M. Fax 343-5787 >F-484 Pavillon Marie-Victorin katherine.hanratty@umontreal.ca ______________________________ Julien Doyon, Ph.D. Département de psychologie Université de Montréal C.P. 6128, Succ. Centre-ville Montréal (Québec) Canada, H3C 3J7 Tel: (514) 343-6502 Fax: (514) 343-5787 e-mail: julien.doyon@umontreal.ca ______________________________