Skip to main content

Table 14 Proportion of over-fitting, 0.0 precision explanations

From: Ada-WHIPS: explaining AdaBoost classification with applications in the health sciences

  SAMME SAMME.R
Data Ada-WHIPS Anchors LORE Ada-WHIPS Anchors LORE
Breast cancer 0 0.01 0.04 0 0.18 0.06
Cardiotocography 0.00 0.07 0.09 0.00 0.08 0.09
Diabetic retinopathy 0 0.15 0.19 0.00 0.13 0.28
Cleveland heart 0 0.03 0.14 0 0.03 0.12
Mental health survey ’16 0 0.00 0.01 0 0.04 0.06
Mental health survey ’14 0 0.01 N/A 0 0.01 N/A
Hospital readmission 0 0.15 N/A 0 0.01 N/A
Thyroid 0 0.03 N/A 0 0.15 N/A
Understanding society 0.00 0.01 N/A 0.01 0.08 N/A