Hi ,
Sorry to post this again. Any help will be greatly appreciated as I am unable to understand the following
We did the following for our GM VBM anaysis
Model 1 First we ran GLM on a control and 4 patient subgroups regressing out only age
Model 2 Then when the reviewer asked us to regress out disease duration and disability score we did this
i.e. GLM on a control and 4 patient subgroups regressiong out age, disease duration and diability score
Now after this run we lost significance in most of the regions between control and patient group 1 (one of the groups among 4 patient groups) which previously (by previously I mean when we used model 1) showed significance.
Question 1
What I am unable to understand is even though controls don't have disease duration and disability score how did regressing out these measures affected the GM VBM results between the patient group 1and the control group. I would expect that the model would affect the results only between patient subgroups and not between control and the patient groups. or am I totally wrong.
Question 2
Since controls don't have disease duration can I run two separate models like this
1) one GLM run comparing control and patient groups regressing out only age
and
2) GLM on patient groups regressing out age, disease duration and disability score
Is this a correct way to regress out the effects of clinical measures or as I did previously ran GLM on all groups i.e. controls, patient groups and also regressing out age, disease duration and disability score.
Thanks very much for your kind help and patience.
Venkat
________________________________
From: FSL - FMRIB's Software Library on behalf of Stephen Smith
Sent: Thu 9/20/2012 3:39 PM
To: [log in to unmask]
Subject: Re: [FSL] VBM analysis regressing out clinical measures a clairification
? surely only the disease group has disease duration defined ?
> Steve
>
> Sorry again if I want to regress out between group disease duration
> effect? How to do this?
>
> Thanks
> Venkat
>
>
> -----Original Message-----
> From: FSL - FMRIB's Software Library on behalf of Stephen Smith
> Sent: Thu 9/20/2012 3:20 PM
> To: [log in to unmask]
> Subject: Re: [FSL] VBM analysis regressing out clinical measures a
> clairification
>
> If they want you to just regress the within-group effect of duration,
> then:
> - demean the set of disease ages
> - pad with zeros for the non-disease subjects.
>
> Cheers.
>
>
>> Hi All,
>>
>> Sorry to post this again and again. We are in the review process on a
>> manuscript so it will be great help to me if someone could clarify the
>> following for me. The reviewer has asked us to regress out the effect of
>> disease duration since I don't have disuration measure for controls how
>> to
>> do this can I leave those cells in my design matrix empty. I tried using
>> NAN and 0 both didn't work.
>>
>>
>> Thanks
>> Venkat
>>
>>
>>
>> ===================================
>>
>>
>> Please consider the environment before printing this e-mail
>>
>> Cleveland Clinic is ranked one of the top hospitals in America by
>> U.S.News
>> & World Report (2012).
>> Visit us online at http://www.clevelandclinic.org <http://www.clevelandclinic.org/> for a complete listing
>> of our services, staff and locations.
>>
>>
>> Confidentiality Note: This message is intended for use only by the
>> individual or entity to which it is addressed and may contain
>> information
>> that is privileged, confidential, and exempt from disclosure under
>> applicable law. If the reader of this message is not the intended
>> recipient or the employee or agent responsible for delivering the
>> message
>> to the intended recipient, you are hereby notified that any
>> dissemination,
>> distribution or copying of this communication is strictly prohibited.
>> If
>> you have received this communication in error, please contact the
>> sender
>> immediately and destroy the material in its entirety, whether electronic
>> or hard copy.
>>
>> Thank you.
>>
>
>
> ===================================
>
>
> Please consider the environment before printing this e-mail
>
> Cleveland Clinic is ranked one of the top hospitals in America by U.S.News
> & World Report (2012).
> Visit us online at http://www.clevelandclinic.org <http://www.clevelandclinic.org/> for a complete listing
> of our services, staff and locations.
>
>
> Confidentiality Note: This message is intended for use only by the
> individual or entity to which it is addressed and may contain information
> that is privileged, confidential, and exempt from disclosure under
> applicable law. If the reader of this message is not the intended
> recipient or the employee or agent responsible for delivering the message
> to the intended recipient, you are hereby notified that any dissemination,
> distribution or copying of this communication is strictly prohibited. If
> you have received this communication in error, please contact the sender
> immediately and destroy the material in its entirety, whether electronic
> or hard copy.
>
> Thank you.
>
>
===================================
Please consider the environment before printing this e-mail
Cleveland Clinic is ranked one of the top hospitals in America by U.S.News & World Report (2012).
Visit us online at http://www.clevelandclinic.org for a complete listing of our services, staff and locations.
Confidentiality Note: This message is intended for use only by the individual or entity to which it is addressed and may contain information that is privileged, confidential, and exempt from disclosure under applicable law. If the reader of this message is not the intended recipient or the employee or agent responsible for delivering the message to the intended recipient, you are hereby notified that any dissemination, distribution or copying of this communication is strictly prohibited. If you have received this communication in error, please contact the sender immediately and destroy the material in its entirety, whether electronic or hard copy.
Thank you.
|