On 8/11/18 12:02 PM, Avi Gharehgazlou wrote:
External Email - Use Caution
Thank you for your reply. I chose the 1.3 threshold based on LGI
papers in the ASD literature, but I will use 2.0.
2 is still too low. You'd need at least 3.
1. By permutation do you mean FDR correction?
External Email - Use Caution
Thank you for your reply. I chose the 1.3 threshold based on LGI papers in
the ASD literature, but I will use 2.0.
1. By permutation do you mean FDR correction?
2. If I use monte carlo at 2.0 (0.01 p-value) would this be okay for LGI,
or do you still
Each row is a subject and each column is a cluster. BTW, a threshold of
1.3 is way too low for lGI. If you want to use a threshold that low, you
should use permutation instead of monte carlo (in general, permutation
is better, but certainly for lGI).
On 8/9/18 1:39 PM, Avi Gharehgazlou wrote:
External Email - Use Caution
Hi experts,
I looked at association between LGI and a behavioural scale on QDEC. after
the analysis, to plot the significant clusters/ blobs, I wanted to export
LGI values for each subject from each significant blob and based on
instructions in
