Skip to main content

Table 2 Mean accuracy and standard error of the mean of each method, calculated over ten replicates each, times 100

From: Bayesian neural networks with variable selection for prediction of genotypic values

Base\(63.6\pm 1.2\)\(63.8\pm 1.2\)\(64.8\pm 1.4\)\(62.5\pm 1.3\)\(61.5\pm 1.5\)\(62.2\pm 1.4\)
\(S_{10}\)\(63.6\pm 1.5\)\(84.6\pm 1.5\)\(91.3\pm 1.3\)\(63.1\pm 1.3\)\(82.0\pm 1.4\)\(62.7\pm 1.4\)
\(S_{100}\)\(61.6\pm 0.7\)\(64.4\pm 1.0\)\(66.8\pm 1.3\)\(61.0\pm 0.6\)\(61.5\pm 1.1\)\(60.7\pm 0.7\)
\(S_{1000}\)\(66.0\pm 1.8\)\(64.9\pm 1.7\)\(66.0\pm 1.8\)\(65.7\pm 1.8\)\(62.9\pm 2.1\)\(65.5\pm 1.8\)
\(D_{\text {medium}}\)\(55.4\pm 2.0\)\(55.6\pm 1.8\)\(56.2\pm 2.1\)\(56.1\pm 2.0\)\(55.4\pm 2.2\)\(55.8\pm 2.0\)
\(D_{\text {extreme}}\)\(42.8\pm 1.7\)\(42.8\pm 1.5\)\(43.4\pm 1.8\)\(49.7\pm 1.7\)\(49.5\pm 1.7\)\(49.2\pm 1.7\)
\(E_A\)\(43.9\pm 2.0\)\(44.0\pm 1.8\)\(44.6\pm 2.1\)\(43.2\pm 2.2\)\(41.4\pm 2.0\)\(43.3\pm 2.4\)
\(E_C\)\(44.9\pm 2.1\)\(44.5\pm 2.4\)\(45.4\pm 2.4\)\(44.5\pm 2.1\)\(43.9\pm 2.4\)\(44.4\pm 2.2\)
\(E_I\)\(56.5\pm 1.5\)\(56.4\pm 1.7\)\(58.0\pm 1.6\)\(55.2\pm 1.5\)\(54.0\pm 1.8\)\(55.2\pm 1.5\)
  1. Each row corresponds to a scenario, as summarized in Table 1. The different columns correspond to different methods, GBLUP and Bayes-B are additive methods, GBLUP-AD and BayesB-AD are methods with additive and dominance features and GBLUP-ADAA has additive, dominance and additive × additive features