Trends in the BA-RB-I coefficients at the three levels of the U-smile method for four new models derived from the training dataset across imbalance ranging from 1% to 99% of the event class.

<p>Two informative variables (ST depression and Str Rnd normal) and two non-informative variables (glucose and Rnd normal) were added to the reference model. Level 1 refers to the subclass-specific coefficients, level 2 to the class-specific net coefficients, and level 3 to the weighted overal...

Full description

Saved in:

Bibliographic Details
Main Author:	Barbara Więckowska (536264) (author)
Other Authors:	Katarzyna B. Kubiak (18585116) (author), Przemysław Guzik (18585122) (author)
Published:	2025
Subjects:	Medicine Science Policy Infectious Diseases Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified proved highly effective net reclassification index nested setting ). matthews correlation coefficient heart disease dataset generated random variables certain traditional measures higher imbalance levels defined imbalance levels imbalanced binary classification xlink "> real using real data reference model overfitted entire imbalance range brier skill score smile method indicated reference prediction model majority class outnumbers new variable added reference model imbalance range class imbalance smile method majority class variable selection prediction improvement imbalanced datasets smile plots smile plot minority class event class class balance weighting factor useful tool seven pre reference models ratio test previously developed point size life problems level approach
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	<p>Two informative variables (ST depression and Str Rnd normal) and two non-informative variables (glucose and Rnd normal) were added to the reference model. Level 1 refers to the subclass-specific coefficients, level 2 to the class-specific net coefficients, and level 3 to the weighted overall coefficients. Smooth curves were fitted using the local polynomial regression fitting (LOESS) method. BA coefficients: average absolute changes in prediction between new and reference models; RB coefficients: relative changes in prediction between new and reference models (relative to the reference prediction error); I coefficients: proportions of individuals with prediction changes in each class.</p>

Trends in the BA-RB-I coefficients at the three levels of the U-smile method for four new models derived from the training dataset across imbalance ranging from 1% to 99% of the event class.

Similar Items