Skip to main content

Table 3 Summary of parameter estimates for the bivariate mixture model averaged over the 156 LOOCV outcomes

From: Gene selection and cancer type classification of diffuse large-B-cell lymphoma using a bivariate mixture model for two-species data

  Parameter
Category Π k μ a k μ h k σ ak 2 ρ k σ a k σ h k σ hk 2
0 0.823(0.077) NE NE 0.013(0.001) NE 0.012(0.001)
1 0.001(0.005) 0.341(0.081) 0.022(0.130) 0.004(0.010) 0.001(0.017) 0.022(0.060)
2 0.001(0.001) -0.602(0.243) -0.831(0.193) 0.199(0.082) -0.128(0.048) 0.089(0.036)
3 0.001(0.004) 0.495(0.195) -0.564(0.244) 0.042(0.078) -0.042(0.041) 0.119(0.074)
4 0.000(0.003) -1.131(0.422) 0.758(0.305) 0.000(0.028) 0.000(0.015) 0.000(0.050)
5 0.020(0.008) NE 0.492(0.121) 0.020(0.021) NE 0.058(0.049)
6 0.011(0.004) NE -0.517(0.136) 0.034(0.093) NE 0.040(0.044)
7 0.130(0.077) 0.331(0.038) NE 0.018(0.009) NE 0.025(0.001)
8 0.012(0.008) -0.478(0.339) NE 0.011(0.051) NE 0.042(0.054)
  1. Numbers in parentheses are the bootstrap standard errors; B=5,000 (the number of bootstrap replications); NE not estimated.