 |
 |
Hello, Demeaning can be considered a _specific_ instance of orthogonalisation wrt an ( implicit or explicit ) global mean. For your model, I am assuming you have a 3 EV design - global mean and two other covariates. Demeaning the two covariates makes them orthogonal to the mean, there is generally no need to orthogonalise further _unless_ you have a particular reason to attribute any joint signal to one or other of the two EVs. Kind Regards Matthew -------------------------------- Dr Matthew Webster FMRIB Centre John Radcliffe Hospital University of Oxford On 20 Aug 2022, at 19:03, d m <[log in to unmask]<mailto:[log in to unmask]>> wrote: Hello, Does orthogonalize and demeaning mean the same thing with respect to covariates in a glm? Running a 1-sample t-test in randomise with 2 additional covariates of interest. If I demean the 2 covariates, does that mean they are orthogonalized to the each other and the mean effect? If not, what additional step must I include to make sure the mean effect and 2 additional covariates of interest are orthogonalized to each other? Thanks. d.m. ________________________________ To unsubscribe from the FSL list, click the following link: https://www.jiscmail.ac.uk/cgi-bin/WA-JISC.exe?SUBED1=FSL&A=1 ######################################################################## To unsubscribe from the FSL list, click the following link: https://www.jiscmail.ac.uk/cgi-bin/WA-JISC.exe?SUBED1=FSL&A=1 This message was issued to members of www.jiscmail.ac.uk/FSL, a mailing list hosted by www.jiscmail.ac.uk, terms & conditions are available at https://www.jiscmail.ac.uk/policyandsecurity/