1.

Record Nr.

UNINA9910799487003321

Autore

Larner A. J

Titolo

The 2x2 Matrix [[electronic resource] ] : Contingency, Confusion and the Metrics of Binary Classification / / by A. J. Larner

Pubbl/distr/stampa

Cham : , : Springer International Publishing : , : Imprint : Springer, , 2024

ISBN

3-031-47194-6

Edizione

[2nd ed. 2024.]

Descrizione fisica

1 online resource (262 pages)

Disciplina

570.15195

Soggetti

Biometry

Neurology

Medical informatics

Machine learning

Biostatistics

Health Informatics

Machine Learning

Lingua di pubblicazione

Inglese

Formato

Materiale a stampa

Livello bibliografico

Monografia

Nota di contenuto

Introduction -- Paired measures -- Paired complementary measures -- Unitary measures -- Number needed (reciprocal) measures and their combinations as likelihoods -- Quality (Q) measures -- Graphing methods -- Other measures, other tables -- Classification of metrics of binary classification.

Sommario/riassunto

This book describes, extends, and illustrates the metrics of binary classification through worked examples. Worked examples based on pragmatic test accuracy study data are used in chapters to illustrate relevance to day-to-day clinical practice. Readers will gain an understanding of sensitivity and specificity and predictive values along with many other parameters. The contents are highly structured, and the use of worked examples facilitates understanding and interpretation. This book is a resource for clinicians in any discipline who are involved in the performance or assessment of test accuracy studies and professionals in the disciplines of machine learning or informatics wishing to gain insight into clinical applications of 2x2



tables.