back to index

Correlation/prediction results for subject measure 250 (AngAggr_Unadj)

818 subjects had a valid AngAggr_Unadj measure.

Multivariate prediction (GLM-based, automatic feature selection, leave-one-family-out prediction)
Original data space: r=0.20 CoD=-0.02     Deconfounded space: r=0.11 CoD=0.01
Scatterplot shows predicted-AngAggr_Unadj vs measured-AngAggr_Unadj (in original and deconfounded data space).

Univariate regression (regressing each netmat element independently against AngAggr_Unadj, correcting for multiple comparisons across elements, using PALM permutation testing, taking into account family structure).
Number of significantly correlated edges at p<0.05 (two-tailed, FWE corrected) = 0 (minimum corrected p = 0.1584)
Number of significantly correlated edges at p<0.05 (two-tailed, uncorrected) = 53 (15 expected by chance)
Image shows edges (node-pairs) whose connection most strongly correlates with AngAggr_Unadj (in decreasing order), with t-statistic listed at the top of each node-pair.