Skip to main content

Table 3 Additive model (ADD).

From: Neural networks for modeling gene-gene interactions in association studies

  Low risk High risk
  a1 = 2 a0; a2 = 4 a0 a1 = 5 a0; a2 = 10 a0
  b1 = 5·b0; b2 = 10 b0 b1 = 5 b0; b2 = 10 b0
Theoretical penetrance matrix
Neural network   
   Mean absolute difference E
   Sum 0.2313 0.2059
Logistic regression   
   Mean absolute difference E
   Sum 0.2530 0.2544
Logistic regression (design variables)   
   Mean absolute difference E
   Sum 0.2897 0.2804
  1. Mean absolute differences between theoretical and estimated penetrance matrices from 100 replications in the low and high risk scenario.