University of Sussex
Browse
BarrettDienesSeth_PSYCHMETH2013.pdf (379.19 kB)

Measures of metacognition on signal-detection theoretic models

Download (379.19 kB)
journal contribution
posted on 2023-06-08, 16:46 authored by Adam BarrettAdam Barrett, Zoltan DienesZoltan Dienes, Anil SethAnil Seth
Analysing metacognition, specifically knowledge of accuracy of internal perceptual, memorial or other knowledge states, is vital for many strands of psychology, including determining the accuracy of feelings of knowing, and discriminating conscious from unconscious cognition. Quantifying metacognitive sensitivity is however more challenging than quantifying basic stimulus sensitivity. Under popular signal detection theory (SDT) models for stimulus classification tasks, approaches based on type II receiver-operator characteristic (ROC) curves or type II d-prime risk confounding metacognition with response biases in either the type I (classification) or type II (metacognitive) tasks. A new approach introduces meta-d': the type I d-prime that would have led to the observed type II data had the subject used all the type I information. Here we (i) further establish the inconsistency of the type II d-prime and ROC approaches with new explicit analyses of the standard SDT model, and (ii) analyse, for the first time, the behaviour of meta-d' under non-trivial scenarios, such as when metacognitive judgments utilize enhanced or degraded versions of the type I evidence. Analytically, meta-d' values typically reflect the underlying model well, and are stable under changes in decision criteria; however, in relatively extreme cases meta-d' can become unstable. We explore bias and variance of in-sample measurements of meta-d' and supply MATLAB code for estimation in general cases. Our results support meta-d' as a useful measure of metacognition, and provide rigorous methodology for its application. Our recommendations are useful for any researchers interested in assessing metacognitive accuracy.

History

Publication status

  • Published

File Version

  • Accepted version

Journal

Psychological Methods.

ISSN

1082-989X

Publisher

American Psychological Association

Issue

4

Volume

18

Page range

535-552

Department affiliated with

  • Informatics Publications

Notes

This article may not exactly replicate the final version published in the APA journal. It is not the copy of record.

Full text available

  • Yes

Peer reviewed?

  • Yes

Legacy Posted Date

2014-02-26

First Open Access (FOA) Date

2014-02-26

First Compliant Deposit (FCD) Date

2014-02-26

Usage metrics

    University of Sussex (Publications)

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC