English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In many binary classification applications such as disease diagnosis and spamdetection, practitioners often face great needs to control type I errors (i.e.,the conditional probability of misclassifying a class 0 observation as class 1)so that it remains below a desired threshold. To address this need, theNeyman-Pearson (NP) classification paradigm is a natural choice; it minimizestype II error (i.e., the conditional probability of misclassifying a class 1observation as class 0) while enforcing an upper bound, $\alpha$, on the type Ierror. Although the NP paradigm has a century-long history in hypothesistesting, it has not been well recognized and implemented in classificationschemes. Common practices that directly limit the empirical type I error to nomore than $\alpha$ do not satisfy the type I error control objective becausethe resulting classifiers are still likely to have type I errors much largerthan $\alpha$. As a result, the NP paradigm has not been properly implementedfor many classification scenarios in practice. In this work, we develop thefirst umbrella algorithm that implements the NP paradigm for all scoring-typeclassification methods, including popular methods such as logistic regression,support vector machines and random forests. Powered by this umbrella algorithm,we propose a novel graphical tool for NP classification methods: NP receiveroperating characteristic (NP-ROC) bands, motivated by the popular receiveroperating characteristic (ROC) curves. NP-ROC bands will help choose $\alpha$in a data adaptive way and compare different NP classifiers. We demonstrate theuse and properties of the NP umbrella algorithm and NP-ROC bands, available inthe R package nproc, through simulation and real data case studies.

Neyman-Pearson (NP) classification algorithms and NP receiver operating characteristics (NP-ROC)