725 subjects had a valid Hematocrit_2 measure.
Multivariate prediction (GLM-based, automatic feature selection, leave-one-family-out prediction)
Original data space: r=0.45 CoD=0.10 Deconfounded space: r=-0.03 CoD=-0.03
Scatterplot shows predicted-Hematocrit_2 vs measured-Hematocrit_2 (in original and deconfounded data space).
Univariate regression (regressing each netmat element independently against Hematocrit_2, 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 = 0.2036)
Number of significantly correlated edges at p<0.05 (two-tailed, uncorrected) = 97 (62 expected by chance)
Image shows edges (node-pairs) whose connection most strongly correlates with Hematocrit_2 (in decreasing order), with t-statistic listed at the top of each node-pair.
