Article

Additive Logistic Models for AUC Classification: Likelihood-Ratio Scoring and Component-wise Interpretability

2026-05-19

Abstract excerpt

<title>Abstract</title> Classification models are often evaluated mainly by predictive performance, yet in many scientific applications they must also explain how individual variables affect risk. This paper addresses this performance--interpretability trade-off for binary classification evaluated by the receiver operating characteristic (ROC) curve and the area under the receiver operating characteristic curv...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: ab664e87-485b-55e0-aabf-981b0a2f10df
DOI: 10.21203/rs.3.rs-9647685/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Additive Logistic Models for AUC Classification: Likelihood-Ratio Scoring and Component-wise InterpretabilityDOI 10.21203/rs.3.rs-9647685/v1Read

ChatGPT-Enhanced ROC Analysis (CERA): A Shiny Web Tool for Finding Optimal Cutoff in Biomarker AnalysisSemantic proximity Read

Visualising the Truth: A Composite Evaluation Framework for Score-Based Predictive Models SelectionSemantic proximity Read

Locally calibrated error rates improve interpretability of AI scores and influence radiologist decision-makingSemantic proximity Read

Bridging Classical Statistics and Modern Data Analysis: A Comprehensive Survey of Generalized Linear ModelsSemantic proximity Read

Non-monotone transformation of biomarkers to improve diagnostic and screening accuracy in a DNA methylation study with trichotomous phenotypes.Semantic proximity Read

Impact of Class Imbalance on Binary Outcome Predictions: A Comparative Study of Thresholding Strategies with LASSOSemantic proximity Read

Evaluating predictive biomarkers for a binary outcome with linear versus logistic regression – Practical recommendations for the choice of the modelSemantic proximity Read

Generalized Bayesian Method for Diagnostic Classification ModelsSemantic proximity Read

A Unified Framework for Statistical Inference and Study Design of Comparative F 1 and F β Scores under Paired Classifier EvaluationsSemantic proximity Read