Re: [Freesurfer] extracting beta coefficients and p-values {Disarmed}

Greve, Douglas N.,Ph.D. Sun, 29 Nov 2020 14:22:46 -0800

Yes, that is correct

On 11/19/2020 11:43 AM, Batool Rizvi wrote:

External Email - Use Caution

Hi Dr. Greve,
Sorry to bring this back up, but I didn't fully understand how to calculate the
variance in order to get the confidence intervals for each covariate, so I
wanted to double check the steps.
A colleague in the lab is helping me to derive the variance using Matlab, and
just wanted to make sure of the formula I would use:

variance of B = rvar.mgh * inverse(transpose(Xg.dat)*(Xg.dat))

Is this the correct formula to derive variance in Matlab?

Thanks again for your help,
Batool

On Fri, Oct 9, 2020 at 5:46 AM Douglas N. Greve
<dgr...@mgh.harvard.edu<mailto:dgr...@mgh.harvard.edu>> wrote:
You can standardize them yourself. rvar.mgh is the residual variance and Xg is
the design matrix. Between those and the beta values, you can standarize the
betas

On 10/7/2020 3:39 PM, Batool Rizvi wrote:

External Email - Use Caution

Hi Dr. Greve,

Thank you for your response! Not sure if you already addressed this, but my
second question was whether there is a way to derive the (95%) confidence
intervals for my covariates that were included in the mri_glmfit analyses?

Thanks again!
Batool

On Wed, Oct 7, 2020 at 7:31 AM Douglas N. Greve
<dgr...@mgh.harvard.edu<mailto:dgr...@mgh.harvard.edu>> wrote:

On 10/6/2020 4:26 PM, Batool Rizvi wrote:

External Email - Use Caution

Hi,

I had a couple additional questions related to this topic.

1. The beta-coefficients I derived from using the mri_segstats command with the
input beta.mgh, are these values unstandardized?
Yes, that have not been standarized

2. Just wondering, is there a possible way to also derive 95% confidence
intervals for my covariates that were included in the mri_glmfit analyses?
You can standardize them yourself. rvar.mgh is the residual variance and Xg is
the design matrix. Between those and the beta values, you can standarize the
betas

Thanks so much for your help!
Batool

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 Mass General Brigham
Compliance HelpLine at
http://www.massgeneralbrigham.org/complianceline<http://secure-web.cisco.com/1lI1JXBJbNdEh_vWxVvI7vyzrsvVPmCL9HF3iY0fBgiBVyt9z34pFH6W30at81W19DyufZwA6-bKtOKzwTfhwSo5fji7q872Tu6orVd-Urbdy8q7sZvRKMXoAe_2oJRrngwhfrwfY5_FTtmaxhnu-RXU8a7wisxW3CK98StFL_HthLlUZayqpPq8aZK034dZYBBiYLX3SZy3i9rBAFDDFURE9FZAXNBOoAI5FHSElBzlTDIwy-jABa1ZcQ1fHAA8n/http%3A%2F%2Fwww.massgeneralbrigham.org%2Fcomplianceline>
. 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
Freesurfer@nmr.mgh.harvard.edu
https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer

Re: [Freesurfer] extracting beta coefficients and p-values {Disarmed}

Reply via email to