When to consult precision-recall curves

Jonathan Cook () and Vikram Ramadas ()
Additional contact information
Jonathan Cook: Public Company Accounting Oversight Board
Vikram Ramadas: Public Company Accounting Oversight Board

Stata Journal, 2020, vol. 20, issue 1, 131-148

Abstract: Receiver operating characteristic (ROC) curves are commonly used to evaluate predictions of binary outcomes. When there is a small percentage of items of interest (as would be the case with fraud detection, for example), ROC curves can provide an inflated view of performance. This can cause challenges in determining which set of predictions is better. In this article, we discuss the condi- tions under which precision-recall curves may be preferable to ROC curves. As an illustrative example, we compare two commonly used fraud predictors (Beneish’s [1999, Financial Analysts Journal 55: 24–36] M score and Dechow et al.’s [2011, Contemporary Accounting Research 28: 17–82] F score) using both ROC and precision-recall curves. To aid the reader with using precision-recall curves, we also introduce the command prcurve to plot them.

Keywords: prcurve; precision-recall curves; classifier evaluation; ROC curves (search for similar items in EconPapers)
Date: 2020
Note: to access software from within Stata, net describe http://www.stata-journal.com/software/sj20-1/st0591/
References: Add references at CitEc
Citations: View citations in EconPapers (4)

Downloads: (external link)
http://hdl.handle.net/10.1177/1536867X20909693

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:tsj:stataj:v:20:y:2020:i:1:p:131-148

Ordering information: This journal article can be ordered from
http://www.stata-journal.com/subscription.html

DOI: 10.1177/1536867X20909693

Access Statistics for this article

Stata Journal is currently edited by Nicholas J. Cox and Stephen P. Jenkins

More articles in Stata Journal from StataCorp LLC
Bibliographic data for series maintained by Christopher F. Baum () and Lisa Gilmore ().