EUVIMEDEUVIMED entdecken
Crossref

Bayesian Inference for Stationary Points in Gaussian Process Regression Models for Event-Related Potentials Analysis

Cheng-Han Yu iD, Meng Li iD, Colin Noe, Simon Fischer-Baum, Marina Vannucci iD

Biometrics · 01.06.2023 · 79 (2) · 629-641

DOI: 10.1111/biom.13621 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biometrics, online erschienen am 08.01.2022. Verfasst von Cheng-Han Yu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mathematical and Statistical Sciences, Marquette University, Milwaukee, Wisconsin, USA. Hauptthemen laut MEDLINE: Electroencephalography, Evoked Potentials. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 25 Literaturangaben. Gefördert von: NSF, National Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Stationary points embedded in the derivatives are often critical for a model to be interpretable and may be considered as key features of interest in many applications. We propose a semiparametric Bayesian model to efficiently infer the locations of stationary points of a nonparametric function, which also produces an estimate of the function. We use Gaussian processes as a flexible prior for the underlying function and impose derivative constraints to control the function's shape via conditioning. We develop an inferential strategy that intentionally restricts estimation to the case of at least one stationary point, bypassing possible mis-specifications in the number of stationary points and avoiding the varying dimension problem that often brings in computational complexity. We illustrate the proposed methods using simulations and then apply the method to the estimation of event-related potentials derived from electroencephalography (EEG) signals. We show how the proposed method automatically identifies characteristic components and their latencies at the individual level, which avoids the excessive averaging across subjects that is routinely done in the field to obtain smooth curves. By applying this approach to EEG data collected from younger and older adults during a speech perception task, we are able to demonstrate how the time course of speech perception processes changes with age.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographyEvoked PotentialsAgedHumansBayes TheoremNormal DistributionYoung Adult

Stichwörter der Autor:innen

Bayesian inferenceERP dataGaussian processderivativessemiparametric

Autor:innen und Institutionen

  • Department of Mathematical and Statistical Sciences, Marquette University, Milwaukee, Wisconsin, USA.
  • Department of Statistics, Rice University, Houston, Texas, USA.
  • Department of Psychological Science, Rice University, Houston, Texas, USA.

ORCID-Profile: Cheng-Han Yu, Meng Li, Marina Vannucci

Förderung

  • NSF
  • National Science Foundation

Zitieren

APA

Yu, C. H., Li, M., Noe, C., Fischer-Baum, S., & Vannucci, M. (2023). Bayesian Inference for Stationary Points in Gaussian Process Regression Models for Event-Related Potentials Analysis. Biometrics, 79(2), 629-641. https://doi.org/10.1111/biom.13621

Vancouver

Yu CH, Li M, Noe C, Fischer-Baum S, Vannucci M. Bayesian Inference for Stationary Points in Gaussian Process Regression Models for Event-Related Potentials Analysis. Biometrics. 2023;79(2):629-641. doi:10.1111/biom.13621

BibTeX
@article{Yu2023,
  author = {Yu, Cheng-Han and Li, Meng and Noe, Colin and Fischer-Baum, Simon and Vannucci, Marina},
  title = {Bayesian Inference for Stationary Points in Gaussian Process Regression Models for Event-Related Potentials Analysis},
  journal = {Biometrics},
  year = {2023},
  volume = {79},
  number = {2},
  pages = {629--641},
  doi = {10.1111/biom.13621}
}
Kostenlos starten →