External Email - Use Caution
Hi,
I am trying to run a multivariable GLM with mri_glmfit and I am currently setting up my fsgd file. I have 9 binary variables and 1 continuous variable. My understanding is that in the fsgd file, my "class" would be every possible combination of these binary variables - which is a lot (hundreds) and setting this up manually doesn't seem reasonable. Is this correct and if so could you recommend another way to run this analysis?
Thanks,
Amanda
You'd have 512 groups total, which is probably way too many regardless of whether you do so manually or automatically. You need to think about how you want to model all those variables since modeling all possible interactions is not going to be possible.
On 11/08/2018 12:45 PM, Worker, Amanda wrote:
External Email - Use Caution
Hi,
I am trying to run a multivariable GLM with mri_glmfit and I am currently setting up my fsgd file. I have 9 binary variables and 1 continuous variable. My understanding is that in the fsgd file, my "class" would be every possible combination of these binary variables
- which is a lot (hundreds) and setting this up manually doesn't seem
reasonable. Is this correct and if so could you recommend another way to run this analysis?
Thanks,
Amanda
Freesurfer mailing list Freesurfer@nmr.mgh.harvard.edu https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer
External Email - Use Caution
Yes. I just want to use 7 of those variables as predictors and 2 as covariates of no interest in a linear regression model
________________________________ From: freesurfer-bounces@nmr.mgh.harvard.edu freesurfer-bounces@nmr.mgh.harvard.edu on behalf of Greve, Douglas N.,Ph.D. DGREVE@mgh.harvard.edu Sent: 08 November 2018 18:03:16 To: freesurfer@nmr.mgh.harvard.edu Subject: Re: [Freesurfer] Multivariable linear regression with binary variables
You'd have 512 groups total, which is probably way too many regardless of whether you do so manually or automatically. You need to think about how you want to model all those variables since modeling all possible interactions is not going to be possible.
On 11/08/2018 12:45 PM, Worker, Amanda wrote:
External Email - Use CautionHi,
I am trying to run a multivariable GLM with mri_glmfit and I am currently setting up my fsgd file. I have 9 binary variables and 1 continuous variable. My understanding is that in the fsgd file, my "class" would be every possible combination of these binary variables
- which is a lot (hundreds) and setting this up manually doesn't seem
reasonable. Is this correct and if so could you recommend another way to run this analysis?
Thanks,
Amanda
Freesurfer mailing list Freesurfer@nmr.mgh.harvard.edu https://emea01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fmail.nmr....
_______________________________________________ Freesurfer mailing list Freesurfer@nmr.mgh.harvard.edu https://emea01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fmail.nmr....
you have to make decisions about which interactions you want to model
On 11/9/18 8:43 AM, Worker, Amanda wrote:
External Email - Use Caution
Yes. I just want to use 7 of those variables as predictors and 2 as covariates of no interest in a linear regression model
________________________________ From: freesurfer-bounces@nmr.mgh.harvard.edumailto:freesurfer-bounces@nmr.mgh.harvard.edu freesurfer-bounces@nmr.mgh.harvard.edumailto:freesurfer-bounces@nmr.mgh.harvard.edu on behalf of Greve, Douglas N.,Ph.D. DGREVE@mgh.harvard.edumailto:DGREVE@mgh.harvard.edu Sent: 08 November 2018 18:03:16 To: freesurfer@nmr.mgh.harvard.edumailto:freesurfer@nmr.mgh.harvard.edu Subject: Re: [Freesurfer] Multivariable linear regression with binary variables
You'd have 512 groups total, which is probably way too many regardless of whether you do so manually or automatically. You need to think about how you want to model all those variables since modeling all possible interactions is not going to be possible.
On 11/08/2018 12:45 PM, Worker, Amanda wrote:
External Email - Use CautionHi,
I am trying to run a multivariable GLM with mri_glmfit and I am currently setting up my fsgd file. I have 9 binary variables and 1 continuous variable. My understanding is that in the fsgd file, my "class" would be every possible combination of these binary variables
- which is a lot (hundreds) and setting this up manually doesn't seem
reasonable. Is this correct and if so could you recommend another way to run this analysis?
Thanks,
Amanda
Freesurfer mailing list Freesurfer@nmr.mgh.harvard.edumailto:Freesurfer@nmr.mgh.harvard.edu https://emea01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fmail.nmr....
_______________________________________________ Freesurfer mailing list Freesurfer@nmr.mgh.harvard.edumailto:Freesurfer@nmr.mgh.harvard.edu https://emea01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fmail.nmr....
_______________________________________________ Freesurfer mailing list Freesurfer@nmr.mgh.harvard.edumailto:Freesurfer@nmr.mgh.harvard.edu https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer
freesurfer@nmr.mgh.harvard.edu
-
Greve, Douglas N.,Ph.D. -
Worker, Amanda