Bootstrapping the P300 in diagnostic psychophysiology: How many iterations are needed?

J. Peter Rosenfeld; Anne Ward; Ewout H. Meijer; Denis Yukhnenko

doi:10.1111/psyp.12789

Bootstrapping the P300 in diagnostic psychophysiology: How many iterations are needed?

J. Peter Rosenfeld^*, Anne Ward, Ewout H. Meijer, Denis Yukhnenko

^*Corresponding author for this work

Psychology

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

13 Scopus citations

Abstract

In psychophysiological research, bootstrapping procedures are often used to classify individual participants. How many iterations are required for a reliable bootstrap test is not universally agreed upon. To investigate the number of iterations needed for a stable bootstrap estimate, we reanalyzed P300 data collected in concealed information test paradigms. We also distinguished between the bootstrap and permutations approaches. We compared results in several studies using 100 versus 1,000 versus 10,000 iterations in the bootstrap, and we concluded that 100 iterations were adequate as results from all three iteration numbers correlated highly.

Original language	English (US)
Pages (from-to)	366-373
Number of pages	8
Journal	Psychophysiology
Volume	54
Issue number	3
DOIs	https://doi.org/10.1111/psyp.12789
State	Published - Mar 1 2017

Keywords

Bootstrapping
P300
Permutations

ASJC Scopus subject areas

Experimental and Cognitive Psychology
Endocrine and Autonomic Systems
Neuropsychology and Physiological Psychology
Neurology
Biological Psychiatry
Cognitive Neuroscience
Developmental Neuroscience
General Neuroscience

Access to Document

10.1111/psyp.12789

Cite this

@article{c8d62fdcf35f47158cbb19c56e7d232a,

title = "Bootstrapping the P300 in diagnostic psychophysiology: How many iterations are needed?",

abstract = "In psychophysiological research, bootstrapping procedures are often used to classify individual participants. How many iterations are required for a reliable bootstrap test is not universally agreed upon. To investigate the number of iterations needed for a stable bootstrap estimate, we reanalyzed P300 data collected in concealed information test paradigms. We also distinguished between the bootstrap and permutations approaches. We compared results in several studies using 100 versus 1,000 versus 10,000 iterations in the bootstrap, and we concluded that 100 iterations were adequate as results from all three iteration numbers correlated highly.",

keywords = "Bootstrapping, P300, Permutations",

author = "Rosenfeld, {J. Peter} and Anne Ward and Meijer, {Ewout H.} and Denis Yukhnenko",

note = "Publisher Copyright: {\textcopyright} 2016 Society for Psychophysiological Research",

year = "2017",

month = mar,

day = "1",

doi = "10.1111/psyp.12789",

language = "English (US)",

volume = "54",

pages = "366--373",

journal = "Psychophysiology",

issn = "0048-5772",

publisher = "John Wiley and Sons Inc.",

number = "3",

}

TY - JOUR

T1 - Bootstrapping the P300 in diagnostic psychophysiology

T2 - How many iterations are needed?

AU - Rosenfeld, J. Peter

AU - Ward, Anne

AU - Meijer, Ewout H.

AU - Yukhnenko, Denis

PY - 2017/3/1

Y1 - 2017/3/1

N2 - In psychophysiological research, bootstrapping procedures are often used to classify individual participants. How many iterations are required for a reliable bootstrap test is not universally agreed upon. To investigate the number of iterations needed for a stable bootstrap estimate, we reanalyzed P300 data collected in concealed information test paradigms. We also distinguished between the bootstrap and permutations approaches. We compared results in several studies using 100 versus 1,000 versus 10,000 iterations in the bootstrap, and we concluded that 100 iterations were adequate as results from all three iteration numbers correlated highly.

AB - In psychophysiological research, bootstrapping procedures are often used to classify individual participants. How many iterations are required for a reliable bootstrap test is not universally agreed upon. To investigate the number of iterations needed for a stable bootstrap estimate, we reanalyzed P300 data collected in concealed information test paradigms. We also distinguished between the bootstrap and permutations approaches. We compared results in several studies using 100 versus 1,000 versus 10,000 iterations in the bootstrap, and we concluded that 100 iterations were adequate as results from all three iteration numbers correlated highly.

KW - Bootstrapping

KW - P300

KW - Permutations

UR - http://www.scopus.com/inward/record.url?scp=85008264558&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85008264558&partnerID=8YFLogxK

U2 - 10.1111/psyp.12789

DO - 10.1111/psyp.12789

M3 - Article

C2 - 27925664

AN - SCOPUS:85008264558

SN - 0048-5772

VL - 54

SP - 366

EP - 373

JO - Psychophysiology

JF - Psychophysiology

IS - 3

ER -

Bootstrapping the P300 in diagnostic psychophysiology: How many iterations are needed?

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this