back to index

Correlation/prediction results for subject measure 70 (ASR_Aggr_Pct)

816 subjects had a valid ASR_Aggr_Pct measure.

Multivariate prediction (GLM-based, automatic feature selection, leave-one-family-out prediction)
Original data space: r=0.02 CoD=-0.32     Deconfounded space: r=-0.00 CoD=-0.00
Scatterplot shows predicted-ASR_Aggr_Pct vs measured-ASR_Aggr_Pct (in original and deconfounded data space).

Univariate regression (regressing each netmat element independently against ASR_Aggr_Pct, 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) = 2 (minimum corrected p = 0.0080)
Number of significantly correlated edges at p<0.05 (two-tailed, uncorrected) = 116 (62 expected by chance)
Image shows edges (node-pairs) whose connection most strongly correlates with ASR_Aggr_Pct (in decreasing order), with t-statistic listed at the top of each node-pair.