757 subjects had a valid Hematocrit_1 measure.
Multivariate prediction (GLM-based, automatic feature selection, leave-one-family-out prediction)
Original data space: r=0.45 CoD=0.11 Deconfounded space: r=-0.08 CoD=-0.02
Scatterplot shows predicted-Hematocrit_1 vs measured-Hematocrit_1 (in original and deconfounded data space).
Univariate regression (regressing each netmat element independently against Hematocrit_1, 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 = 0.2588)
Number of significantly correlated edges at p<0.05 (two-tailed, uncorrected) = 21 (15 expected by chance)
Image shows edges (node-pairs) whose connection most strongly correlates with Hematocrit_1 (in decreasing order), with t-statistic listed at the top of each node-pair.
