Maximin and maximin-efficient event-related fmri designs under a nonlinear model

Ming-Hung Kao, Dibyen Majumdar, Abhyuday Mandal, John Stufken

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Previous studies on event-related functional magnetic resonance imaging experimental designs are primarily based on linear models, in which a known shape of the hemodynamic response function (HRF) is assumed. However, the HRF shape is usually uncertain at the design stage. To address this issue, we consider a nonlinear model to accommodate a wide spectrum of feasible HRF shapes, and propose efficient approaches for obtaining maximin and maximin-efficient designs. Our approaches involve a reduction in the parameter space and a search algorithm that helps to efficiently search over a restricted class of designs for good designs. The obtained designs are compared with traditional designs widely used in practice. We also demonstrate the usefulness of our approaches via a motivating example.

Original languageEnglish (US)
Pages (from-to)1940-1959
Number of pages20
JournalAnnals of Applied Statistics
Volume7
Issue number4
DOIs
StatePublished - 2013

Fingerprint

Maximin
Nonlinear Model
Hemodynamics
Response Function
Functional Magnetic Resonance Imaging
Experimental design
Design of experiments
Search Algorithm
Parameter Space
Design
Linear Model
Demonstrate

Keywords

  • A-optimality
  • Cyclic permutation
  • Design efficiency
  • Genetic algorithms
  • Hemodynamic response function
  • Information matrix

ASJC Scopus subject areas

  • Statistics, Probability and Uncertainty
  • Modeling and Simulation
  • Statistics and Probability

Cite this

Maximin and maximin-efficient event-related fmri designs under a nonlinear model. / Kao, Ming-Hung; Majumdar, Dibyen; Mandal, Abhyuday; Stufken, John.

In: Annals of Applied Statistics, Vol. 7, No. 4, 2013, p. 1940-1959.

Research output: Contribution to journalArticle

Kao, Ming-Hung ; Majumdar, Dibyen ; Mandal, Abhyuday ; Stufken, John. / Maximin and maximin-efficient event-related fmri designs under a nonlinear model. In: Annals of Applied Statistics. 2013 ; Vol. 7, No. 4. pp. 1940-1959.
@article{ab41a6e3158f4af59bc7be90f8da877a,
title = "Maximin and maximin-efficient event-related fmri designs under a nonlinear model",
abstract = "Previous studies on event-related functional magnetic resonance imaging experimental designs are primarily based on linear models, in which a known shape of the hemodynamic response function (HRF) is assumed. However, the HRF shape is usually uncertain at the design stage. To address this issue, we consider a nonlinear model to accommodate a wide spectrum of feasible HRF shapes, and propose efficient approaches for obtaining maximin and maximin-efficient designs. Our approaches involve a reduction in the parameter space and a search algorithm that helps to efficiently search over a restricted class of designs for good designs. The obtained designs are compared with traditional designs widely used in practice. We also demonstrate the usefulness of our approaches via a motivating example.",
keywords = "A-optimality, Cyclic permutation, Design efficiency, Genetic algorithms, Hemodynamic response function, Information matrix",
author = "Ming-Hung Kao and Dibyen Majumdar and Abhyuday Mandal and John Stufken",
year = "2013",
doi = "10.1214/13-AOAS658",
language = "English (US)",
volume = "7",
pages = "1940--1959",
journal = "Annals of Applied Statistics",
issn = "1932-6157",
publisher = "Institute of Mathematical Statistics",
number = "4",

}

TY - JOUR

T1 - Maximin and maximin-efficient event-related fmri designs under a nonlinear model

AU - Kao, Ming-Hung

AU - Majumdar, Dibyen

AU - Mandal, Abhyuday

AU - Stufken, John

PY - 2013

Y1 - 2013

N2 - Previous studies on event-related functional magnetic resonance imaging experimental designs are primarily based on linear models, in which a known shape of the hemodynamic response function (HRF) is assumed. However, the HRF shape is usually uncertain at the design stage. To address this issue, we consider a nonlinear model to accommodate a wide spectrum of feasible HRF shapes, and propose efficient approaches for obtaining maximin and maximin-efficient designs. Our approaches involve a reduction in the parameter space and a search algorithm that helps to efficiently search over a restricted class of designs for good designs. The obtained designs are compared with traditional designs widely used in practice. We also demonstrate the usefulness of our approaches via a motivating example.

AB - Previous studies on event-related functional magnetic resonance imaging experimental designs are primarily based on linear models, in which a known shape of the hemodynamic response function (HRF) is assumed. However, the HRF shape is usually uncertain at the design stage. To address this issue, we consider a nonlinear model to accommodate a wide spectrum of feasible HRF shapes, and propose efficient approaches for obtaining maximin and maximin-efficient designs. Our approaches involve a reduction in the parameter space and a search algorithm that helps to efficiently search over a restricted class of designs for good designs. The obtained designs are compared with traditional designs widely used in practice. We also demonstrate the usefulness of our approaches via a motivating example.

KW - A-optimality

KW - Cyclic permutation

KW - Design efficiency

KW - Genetic algorithms

KW - Hemodynamic response function

KW - Information matrix

UR - http://www.scopus.com/inward/record.url?scp=84886732725&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84886732725&partnerID=8YFLogxK

U2 - 10.1214/13-AOAS658

DO - 10.1214/13-AOAS658

M3 - Article

AN - SCOPUS:84886732725

VL - 7

SP - 1940

EP - 1959

JO - Annals of Applied Statistics

JF - Annals of Applied Statistics

SN - 1932-6157

IS - 4

ER -