If contrast*beta>0, then the t-statistic is positive.
If contrast*beta<0, then the t-statistic is negative.
Best Regards, Donald McLaren
=================
D.G. McLaren, Ph.D.
Postdoctoral Research Fellow, GRECC, Bedford VA
Research Fellow, Department of Neurology, Massachusetts General
Hospital and Harvard Medical School
Office: (773) 406-2464
=====================
This e-mail contains CONFIDENTIAL INFORMATION which may contain
PROTECTED HEALTHCARE INFORMATION and may also be LEGALLY PRIVILEGED
and which is intended only for the use of the individual or entity
named above. If the reader of the e-mail is not the intended recipient
or the employee or agent responsible for delivering it to the intended
recipient, you are hereby notified that you are in possession of
confidential and privileged information. Any unauthorized use,
disclosure, copying or the taking of any action in reliance on the
contents of this information is strictly prohibited and may be
unlawful. If you have received this e-mail unintentionally, please
immediately notify the sender via telephone at (773) 406-2464 or
email.
On Fri, Feb 25, 2011 at 12:25 AM, Israr Ul Haq <[log in to unmask]> wrote:
> Dear Donald,
>
> I remember reading about beta and the GLM and how its calculated by using the matrix inverse, when I first started out reading about it. For some reason I formed the whole concept of individual correlations for each time point of a voxel and the subsequent distribution with its mean and sd as a way of representing what actually beta is representing, the weights of columns. Perhaps because the visualization came easier. Thankyou very much for taking time to point this out.
>
> What I understand from your explanation is that contrast*beta is essentially the output of adding and subtracting the individual values of the betas, based on the 1's and the -1's in the contrast, 1 meaning the beta will be added and -1, it will be subtracted. I guess for my question about the direction of change in terms of betas, how does the t statistic differ between a certain value of contrast*beta and an equal but a negative value of the same. Since the absolute difference between the effect and the mean is the same, does it take into account whether the contrast*beta is a positive or a negative value?
>
> Thanks
> Israr
>
>
|