History of AFNI updates  

|
May 12, 2004 12:04PM
Hi Shruti,

Yes, you are right. I forgot to say that the output from -nodata option provides the normalized standard deviation for each parameter estimate, which is the square root of the diagonal element of overlap correction matrix (X'X)^(-1). The two standard deviations should be roughly proportional to one over the square root of their corresponding sample size of events.

Gang
Subject Author Posted

unequal number of events

Shruti May 10, 2004 04:01PM

Re: unequal number of events

Ziad S. Saad May 12, 2004 10:16AM

Re: unequal number of events

Gang Chen May 12, 2004 10:50AM

Re: unequal number of events

Shruti May 12, 2004 11:45AM

Re: unequal number of events

Gang Chen May 12, 2004 12:04PM