Posterior means (m), standard deviation (SD) (in parentheses), and highest posterior densities (HPD) regions for the residual (Embedded Image), sire (Embedded Image), nonparametric coefficient (Embedded Image), and marker (Embedded Image) variances, and heritability (h2), by model

ParameterPosterior featuresE-BLUPEmbedded Image-metricRKHSBR
Embedded Imagem (SD)24.38 (3.88)29.97 (3.22)17.07 (3.02)20.74 (2.87)
HPD (95%)16.88–32.0424.33–36.8611.78–23.6415.65–26.98
Varianceam (SD)0.10 (0.06)0.40 (0.07)1.05 (0.88)
HPD (95%)0.03–0.240.28–0.550.67–2.02
h2m (SD)0.02 (0.01)
HPD (95%)0.004–0.050
  • E-BLUP, Bayesian linear model; Embedded Image-metric, linear regression on SNPs based on the Embedded Image-metric; RKHS, reproducing kernel Hilbert spaces regression; BR, Bayesian regression.

  • a Sire variance (Embedded Image) for E-BLUP, nonparametric coefficient variances (Embedded Image) for RKHS, and genetic variance associated with the 1000 markers (Embedded Image) for BR.