AFNI Message Board

Dear AFNI users-

We are very pleased to announce that the new AFNI Message Board framework is up! Please join us at:

https://discuss.afni.nimh.nih.gov

Existing user accounts have been migrated, so returning users can login by requesting a password reset. New users can create accounts, as well, through a standard account creation process. Please note that these setup emails might initially go to spam folders (esp. for NIH users!), so please check those locations in the beginning.

The current Message Board discussion threads have been migrated to the new framework. The current Message Board will remain visible, but read-only, for a little while.

Sincerely, AFNI HQ

History of AFNI updates  

|
February 07, 2023 08:07PM
Hi Catherine,

Thank you for the reminder.

I don't recall what I was thinking back then (big surprise), but there are some notable points from that mmms output.

There are 4 matrix columns that show min = max = stdev = 0, and 2 that are very close to that. What do these 6 columns look like?
I suppose 43, 44, 49 and 50 are all zero. But 42 and 48 are surely close to that. Any all-zero columns will lead to warnings.

col 42: min = -0.0000, mean = 0.0000, max = 0.0001, stdev = 0.0000
col 43: min = -0.0000, mean = -0.0000, max = 0.0000, stdev = 0.0000
col 44: min = -0.0000, mean = -0.0000, max = 0.0000, stdev = 0.0000
col 48: min = -0.0000, mean = 0.0000, max = 0.0001, stdev = 0.0000
col 49: min = -0.0000, mean = 0.0000, max = 0.0000, stdev = 0.0000
col 50: min = -0.0000, mean = 0.0000, max = 0.0000, stdev = 0.0000

There are also many columns that have identical mmms results, though that does not imply they are the same. But moving the "col xxx:" text to the end of the line and sorting, we see these all have the same output (for example, there are other sets as well):

min = 0.0000, mean = 0.0010, max = 1.0000, stdev = 0.0320 col 164:
min = 0.0000, mean = 0.0010, max = 1.0000, stdev = 0.0320 col 165:
min = 0.0000, mean = 0.0010, max = 1.0000, stdev = 0.0320 col 166:
min = 0.0000, mean = 0.0010, max = 1.0000, stdev = 0.0320 col 167:
min = 0.0000, mean = 0.0010, max = 1.0000, stdev = 0.0320 col 168:
min = 0.0000, mean = 0.0010, max = 1.0000, stdev = 0.0320 col 169:
min = 0.0000, mean = 0.0010, max = 1.0000, stdev = 0.0320 col 170:
min = 0.0000, mean = 0.0010, max = 1.0000, stdev = 0.0320 col 171:
min = 0.0000, mean = 0.0010, max = 1.0000, stdev = 0.0320 col 172:
min = 0.0000, mean = 0.0010, max = 1.0000, stdev = 0.0320 col 173:
min = 0.0000, mean = 0.0010, max = 1.0000, stdev = 0.0320 col 174:
min = 0.0000, mean = 0.0010, max = 1.0000, stdev = 0.0320 col 175:
min = 0.0000, mean = 0.0010, max = 1.0000, stdev = 0.0320 col 176:
min = 0.0000, mean = 0.0010, max = 1.0000, stdev = 0.0320 col 177:
min = 0.0000, mean = 0.0010, max = 1.0000, stdev = 0.0320 col 178:
min = 0.0000, mean = 0.0010, max = 1.0000, stdev = 0.0320 col 179:
min = 0.0000, mean = 0.0010, max = 1.0000, stdev = 0.0320 col 180:
min = 0.0000, mean = 0.0010, max = 1.0000, stdev = 0.0320 col 181:
min = 0.0000, mean = 0.0010, max = 1.0000, stdev = 0.0320 col 182:
min = 0.0000, mean = 0.0010, max = 1.0000, stdev = 0.0320 col 183:

So start by looking at how these were created, and see if there is anything peculiar in those timing files. Please feel free to post timing files that you are concerned about.

- rick
Subject Author Posted

Collinearity Warning with 3dREMLfit

Catherine Tallman January 10, 2023 12:47PM

Re: Collinearity Warning with 3dREMLfit

rick reynolds January 10, 2023 05:09PM

Re: Collinearity Warning with 3dREMLfit

Catherine Tallman January 15, 2023 03:18PM

Re: Collinearity Warning with 3dREMLfit

Catherine Tallman February 07, 2023 05:19PM

Re: Collinearity Warning with 3dREMLfit

rick reynolds February 07, 2023 08:07PM

Re: Collinearity Warning with 3dREMLfit

Catherine Tallman February 14, 2023 05:10PM

Re: Collinearity Warning with 3dREMLfit

Catherine Tallman February 27, 2023 02:36PM

Re: Collinearity Warning with 3dREMLfit

rick reynolds February 27, 2023 03:15PM

Re: Collinearity Warning with 3dREMLfit

rick reynolds March 06, 2023 04:27PM