One Sample and Paired T-Test

Usage One Sample

Determine if the mean of the values for each node are significantly different than a specified constant (typically zero).

Usage Paired

The Paired T-Test is also referred to as a T-Test for Dependent Means.

The input metric/shape files must have the same number of columns and the corresponding columns in the two input files are assumed to be the same subject.  For each node, subtract the corresponding columns in the input files and determine if their difference is significantly different than a specified constant (typically zero).



T-Value Formula

T = [mean - constant] / [sample-std-dev / sqrt(N)]

Create Real T-Map

Permutation T-Map

For the number of iterations
  1. Generate an array containing N elements where each element is a randomly generated plus or minus one.
  2. Multiple the elements in the array by the corresponding element in each row of the input metric/shape file.
  3. Compute the T-Value for each node.
  4. Add the T-Value for each node to the output permutation T-Map file.

Create Output Report

  1. Find the biggest cluster in each column of the permutation T-Map metric/shape file and sort them by cluster size.
  2. Find the largest (alpha)(iterations) clusters in the Permutation T-Map and use its cluster size as the Significant Cluster Cutoff.
  3. Find clusters in the Real T-Map file.
  4. Report all clusters in Real T-Map file that are larger than Significant Cluster Cutoff.
  5. Create a paint file showing all significant clusters in Real T-Map file.  Name them plus/minus based upon the threshold they exceed.