Signal detection theory, the approach of choice : model-based and distribution-free measures and evaluation

D. Kornbrot

Signal detection theory, the approach of choice : model-based and distribution-free measures and evaluation

D. Kornbrot

Research output: Contribution to journal › Article › peer-review

38 Citations (Scopus)

338 Downloads (Pure)

Abstract

New and old methods of analyzing two-choice experiments with confidence ratings are evaluated. These include the theory of signal detectability (TSD), Luce's choice theory, nonparametric techniques based on areas under receiver-operating characteristic (ROC) ftmctions, and methods based on S' and Omega, proposed by Balakrishnan and his colleagues. New methods for assessing the bias of a complete ROC function are proposed, together with an additional area-based measure of response bias. Area measures of both sensitivity and bias proved the most consistent. Response bias for a full ROC function was larger than bias at the cut point and also provided additional information. Participants showed voluntary control of bias for all measures except Omega. Unequal variance versions of TSD and choice models gave similar fits to data, with the choice model closer to an equal variance version. Discrimination data from Balakrishnan (1999) formed the empirical test bed.

Original language	English
Pages (from-to)	393-414
Journal	Perception & Psychophysics
Volume	68
Issue number	3
Publication status	Published - 2006

Keywords

decision
bias
categorization

Access to Document

Kornbrot05J P P bias finaproof
"This manuscript was accepted for publication in Perception and Psychophysics in 2006. The copyright is held by Psychonomic Society Publications. This document may not exactly correspond to the final published version. Psychonomic Society Publications disclaims any responsibility or liability for errors in this manuscript."
Accepted author manuscript, 434 KB

Cite this

@article{58e36cb0c0424057a2ad3c289b664b05,

title = "Signal detection theory, the approach of choice : model-based and distribution-free measures and evaluation",

abstract = "New and old methods of analyzing two-choice experiments with confidence ratings are evaluated. These include the theory of signal detectability (TSD), Luce's choice theory, nonparametric techniques based on areas under receiver-operating characteristic (ROC) ftmctions, and methods based on S' and Omega, proposed by Balakrishnan and his colleagues. New methods for assessing the bias of a complete ROC function are proposed, together with an additional area-based measure of response bias. Area measures of both sensitivity and bias proved the most consistent. Response bias for a full ROC function was larger than bias at the cut point and also provided additional information. Participants showed voluntary control of bias for all measures except Omega. Unequal variance versions of TSD and choice models gave similar fits to data, with the choice model closer to an equal variance version. Discrimination data from Balakrishnan (1999) formed the empirical test bed.",

keywords = "decision, bias, categorization",

author = "D. Kornbrot",

note = "{"}This manuscript was accepted for publication in Perception and Psychophysics in 2006. The copyright is held by Psychonomic Society Publications. This document may not exactly correspond to the final published version. Psychonomic Society Publications disclaims any responsibility or liability for errors in this manuscript.{"} Original article can be found at : http://app.psychonomic-journals.org/",

year = "2006",

language = "English",

volume = "68",

pages = "393--414",

journal = "Perception & Psychophysics",

issn = "0031-5117",

publisher = "Psychonomic Society Inc.",

number = "3",

}

TY - JOUR

T1 - Signal detection theory, the approach of choice : model-based and distribution-free measures and evaluation

AU - Kornbrot, D.

N1 - "This manuscript was accepted for publication in Perception and Psychophysics in 2006. The copyright is held by Psychonomic Society Publications. This document may not exactly correspond to the final published version. Psychonomic Society Publications disclaims any responsibility or liability for errors in this manuscript." Original article can be found at : http://app.psychonomic-journals.org/

PY - 2006

Y1 - 2006

N2 - New and old methods of analyzing two-choice experiments with confidence ratings are evaluated. These include the theory of signal detectability (TSD), Luce's choice theory, nonparametric techniques based on areas under receiver-operating characteristic (ROC) ftmctions, and methods based on S' and Omega, proposed by Balakrishnan and his colleagues. New methods for assessing the bias of a complete ROC function are proposed, together with an additional area-based measure of response bias. Area measures of both sensitivity and bias proved the most consistent. Response bias for a full ROC function was larger than bias at the cut point and also provided additional information. Participants showed voluntary control of bias for all measures except Omega. Unequal variance versions of TSD and choice models gave similar fits to data, with the choice model closer to an equal variance version. Discrimination data from Balakrishnan (1999) formed the empirical test bed.

AB - New and old methods of analyzing two-choice experiments with confidence ratings are evaluated. These include the theory of signal detectability (TSD), Luce's choice theory, nonparametric techniques based on areas under receiver-operating characteristic (ROC) ftmctions, and methods based on S' and Omega, proposed by Balakrishnan and his colleagues. New methods for assessing the bias of a complete ROC function are proposed, together with an additional area-based measure of response bias. Area measures of both sensitivity and bias proved the most consistent. Response bias for a full ROC function was larger than bias at the cut point and also provided additional information. Participants showed voluntary control of bias for all measures except Omega. Unequal variance versions of TSD and choice models gave similar fits to data, with the choice model closer to an equal variance version. Discrimination data from Balakrishnan (1999) formed the empirical test bed.

KW - decision

KW - bias

KW - categorization

M3 - Article

SN - 0031-5117

VL - 68

SP - 393

EP - 414

JO - Perception & Psychophysics

JF - Perception & Psychophysics

IS - 3

ER -

Signal detection theory, the approach of choice : model-based and distribution-free measures and evaluation

Abstract

Keywords

Access to Document

Fingerprint

Cite this