Re: [HCP-Users] Infinite values in Group average data

2017-05-15 Thread Glasser, Matthew
ilto:tsc...@mst.edu>> Cc: "hcp-users@humanconnectome.org<mailto:hcp-users@humanconnectome.org>" <hcp-users@humanconnectome.org<mailto:hcp-users@humanconnectome.org>> Subject: Re: [HCP-Users] Infinite values in Group average data This makes more sense! Sorry I missed y

Re: [HCP-Users] Infinite values in Group average data

2017-05-15 Thread Sang-Yun Oh
This makes more sense! Sorry I missed your mention of fisher-z transform So I would apply tanh to each element to revert back to regular correlation coefficients Thank you for your help! Best, Sang On Mon, May 15, 2017 at 5:57 PM Timothy Coalson wrote: > After the fisher-z

Re: [HCP-Users] Infinite values in Group average data

2017-05-15 Thread Timothy Coalson
After the fisher-z transform, you can have values greater than 1, see the graph on the right: https://en.wikipedia.org/wiki/Fisher_transformation This is why the "correct" answer for the diagonal is infinity for the "zcorr" file. Tim On Mon, May 15, 2017 at 7:51 PM, Sang-Yun Oh

Re: [HCP-Users] Infinite values in Group average data

2017-05-15 Thread Sang-Yun Oh
I am also finding that some off-diagonal elements in this matrix are also greater than 1 indicating this matrix is not a correlation matrix. In [5]: img Out[5]: memmap([[ 8.66434002e+00, 1.96847185e-01, 1.66294336e-01, ..., 1.01449557e-01, 7.45474100e-02, 1.15624115e-01],

Re: [HCP-Users] Infinite values in Group average data

2017-05-15 Thread Sang-Yun Oh
Thank you for the response. I am, too, confused by some being non-zero finite values, and others being infinities. Before computing a correlation matrix, if standardized by subtracting the mean and scaling by variance, all diagonal elements should be exactly 1. What I am concerned about is how

Re: [HCP-Users] Infinite values in Group average data

2017-05-15 Thread Timothy Coalson
Per the name "zcorr", the correlation values have been z-transformed (fisher's small z transform). I am somewhat confused as to why some elements in the diagonal are not infinite. The "true" value of applying this transform would be infinite on the entire diagonal, as arctanh(1) is infinite. I

[HCP-Users] Infinite values in Group average data

2017-05-15 Thread Sang-Yun Oh
I downloaded group average functional correlation file: HCP_S900_820_rfMRI_MSMAll_groupPCA_d4500ROW_zcorr.dconn.nii Some diagonal elements of the square matrix (91282x91282) are infinite (Please see below). I want to use this matrix in ananalysis; however, I am not sure how to understand or deal