Origin of 'ROC' in ROC-curves (signal detection theory)

greenspun.com : LUSENET : History & Theory of Psychology : One Thread

I've been studying signal detection theory a bit, and have come upon a few explanations of the origin of the term 'ROC-curve'. ROC stands for 'receiver operator characteristic' and most texts point out that this originated from radar-technical work in WW2. I haven't been able to find detailed information about this WW2-work though. Do any of you know where there is information available about the 'original' signal detection work?

-- Casper Hulshof (c.d.hulshof@utwente.nl), February 20, 2003

Answers

I'd check the bibliography in John Swet's classic book":

Signal Detection and Recognition by Human Observers -- Edited by John A. Swets in 1964, this book was the first to bring together into one volume a broad discussion coverage of modern signal detection theory applications to human performance, specifically in auditory and visual sensory tasks. Applications address problems in psychology including the integration of sensory information, signal uncertainty, auditory frequency analysis, speech communication, vigilance and recognition memory. Bibliography updated to 1988. Hardcover. 734 pages.

Also, when I searched PsycInfo ROC was used to describe RELATIVE (not receiver) operator characteristic in Swets' work.

-- Hendrika Vande Kemp (hendrika@earthlink.net), February 20, 2003.


Moderation questions? read the FAQ