Permutation tests for detecting and estimating mixtures in task performance within groups

Yungtai Lo, Steven Matthysse, Donald B. Rubin, Philip S. Holzman

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

We propose a two-sample permutation test incorporating mixture models as a general tool for detecting and quantifying effects on task performance. We illustrate the proposed method with examples where the dependent measures under investigation are recorded for normal controls and relatives of patients with schizophrenia on a delayed response, spatial and object working memory task. Our mixture modelling in relatives allows the component distributions to arise from different continuous parametric families. We also investigate the effects of the within-family correlation and the prior distribution of the mixing proportion on the test results. The power of the test depends on sample sizes, the mixing proportion, the difference in component means and the ratio of component variances.

Original languageEnglish (US)
Pages (from-to)1937-1953
Number of pages17
JournalStatistics in Medicine
Volume21
Issue number13
DOIs
StatePublished - Jul 15 2002

Fingerprint

Permutation Test
Task Performance and Analysis
Proportion
Working Memory
Two-sample Test
Mixture Modeling
Components of Variance
Prior distribution
Mixture Model
Sample Size
Dependent
Short-Term Memory
Schizophrenia
Family
Object

Keywords

  • EM algorithm
  • Maximum likelihood
  • Mixture distribution
  • Permutation test
  • Schizophrenia
  • Working memory

ASJC Scopus subject areas

  • Epidemiology

Cite this

Permutation tests for detecting and estimating mixtures in task performance within groups. / Lo, Yungtai; Matthysse, Steven; Rubin, Donald B.; Holzman, Philip S.

In: Statistics in Medicine, Vol. 21, No. 13, 15.07.2002, p. 1937-1953.

Research output: Contribution to journalArticle

Lo, Yungtai ; Matthysse, Steven ; Rubin, Donald B. ; Holzman, Philip S. / Permutation tests for detecting and estimating mixtures in task performance within groups. In: Statistics in Medicine. 2002 ; Vol. 21, No. 13. pp. 1937-1953.
@article{9ccd62230962458d8d3582e835718ad9,
title = "Permutation tests for detecting and estimating mixtures in task performance within groups",
abstract = "We propose a two-sample permutation test incorporating mixture models as a general tool for detecting and quantifying effects on task performance. We illustrate the proposed method with examples where the dependent measures under investigation are recorded for normal controls and relatives of patients with schizophrenia on a delayed response, spatial and object working memory task. Our mixture modelling in relatives allows the component distributions to arise from different continuous parametric families. We also investigate the effects of the within-family correlation and the prior distribution of the mixing proportion on the test results. The power of the test depends on sample sizes, the mixing proportion, the difference in component means and the ratio of component variances.",
keywords = "EM algorithm, Maximum likelihood, Mixture distribution, Permutation test, Schizophrenia, Working memory",
author = "Yungtai Lo and Steven Matthysse and Rubin, {Donald B.} and Holzman, {Philip S.}",
year = "2002",
month = "7",
day = "15",
doi = "10.1002/sim.1140",
language = "English (US)",
volume = "21",
pages = "1937--1953",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "13",

}

TY - JOUR

T1 - Permutation tests for detecting and estimating mixtures in task performance within groups

AU - Lo, Yungtai

AU - Matthysse, Steven

AU - Rubin, Donald B.

AU - Holzman, Philip S.

PY - 2002/7/15

Y1 - 2002/7/15

N2 - We propose a two-sample permutation test incorporating mixture models as a general tool for detecting and quantifying effects on task performance. We illustrate the proposed method with examples where the dependent measures under investigation are recorded for normal controls and relatives of patients with schizophrenia on a delayed response, spatial and object working memory task. Our mixture modelling in relatives allows the component distributions to arise from different continuous parametric families. We also investigate the effects of the within-family correlation and the prior distribution of the mixing proportion on the test results. The power of the test depends on sample sizes, the mixing proportion, the difference in component means and the ratio of component variances.

AB - We propose a two-sample permutation test incorporating mixture models as a general tool for detecting and quantifying effects on task performance. We illustrate the proposed method with examples where the dependent measures under investigation are recorded for normal controls and relatives of patients with schizophrenia on a delayed response, spatial and object working memory task. Our mixture modelling in relatives allows the component distributions to arise from different continuous parametric families. We also investigate the effects of the within-family correlation and the prior distribution of the mixing proportion on the test results. The power of the test depends on sample sizes, the mixing proportion, the difference in component means and the ratio of component variances.

KW - EM algorithm

KW - Maximum likelihood

KW - Mixture distribution

KW - Permutation test

KW - Schizophrenia

KW - Working memory

UR - http://www.scopus.com/inward/record.url?scp=0037100247&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037100247&partnerID=8YFLogxK

U2 - 10.1002/sim.1140

DO - 10.1002/sim.1140

M3 - Article

VL - 21

SP - 1937

EP - 1953

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 13

ER -