Sample size calculation for multiple testing in microarray data analysis

Sin Ho Jung, Heejung Bang, Stanley Young

Research output: Contribution to journalArticle

60 Citations (Scopus)

Abstract

Microarray technology is rapidly emerging for genome-wide screening of differentially expressed genes between clinical subtypes or different conditions of human diseases. Traditional statistical testing approaches, such as the two-sample t-test or Wilcoxon test, are frequently used for evaluating statistical significance of informative expressions but require adjustment for large-scale multiplicity. Due to its simplicity, Bonferroni adjustment has been widely used to circumvent this problem. It is well known, however, that the standard Bonferroni test is often very conservative. In the present paper, we compare three multiple testing procedures in the microarray context: the original Bonferroni method, a Bonferroni-type improved single-step method and a step-down method. The latter two methods are based on nonparametric resampling, by which the null distribution can be derived with the dependency structure among gene expressions preserved and the family-wise error rate accurately controlled at the desired level. We also present a sample size calculation method for designing microarray studies. Through simulations and data analyses, we find that the proposed methods for testing and sample size calculation are computationally fast and control error and power precisely.

Original languageEnglish (US)
Pages (from-to)157-169
Number of pages13
JournalBiostatistics
Volume6
Issue number1
DOIs
StatePublished - 2005
Externally publishedYes

Fingerprint

Microarray Data Analysis
Sample Size Calculation
Multiple Testing
Microarray Analysis
Sample Size
Bonferroni
Microarray
Adjustment
Familywise Error Rate
Wilcoxon Test
Two-sample Test
Testing
t-test
Null Distribution
Statistical Significance
Error Control
Power Control
Resampling
Gene Expression
Screening

Keywords

  • Adjusted p-value
  • Bonferroni
  • Multi-step
  • Permutation
  • Simulation
  • Single-step

ASJC Scopus subject areas

  • Medicine(all)
  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Sample size calculation for multiple testing in microarray data analysis. / Jung, Sin Ho; Bang, Heejung; Young, Stanley.

In: Biostatistics, Vol. 6, No. 1, 2005, p. 157-169.

Research output: Contribution to journalArticle

Jung, Sin Ho ; Bang, Heejung ; Young, Stanley. / Sample size calculation for multiple testing in microarray data analysis. In: Biostatistics. 2005 ; Vol. 6, No. 1. pp. 157-169.
@article{4d0ed70e41564f5da8d4e34b1c37d262,
title = "Sample size calculation for multiple testing in microarray data analysis",
abstract = "Microarray technology is rapidly emerging for genome-wide screening of differentially expressed genes between clinical subtypes or different conditions of human diseases. Traditional statistical testing approaches, such as the two-sample t-test or Wilcoxon test, are frequently used for evaluating statistical significance of informative expressions but require adjustment for large-scale multiplicity. Due to its simplicity, Bonferroni adjustment has been widely used to circumvent this problem. It is well known, however, that the standard Bonferroni test is often very conservative. In the present paper, we compare three multiple testing procedures in the microarray context: the original Bonferroni method, a Bonferroni-type improved single-step method and a step-down method. The latter two methods are based on nonparametric resampling, by which the null distribution can be derived with the dependency structure among gene expressions preserved and the family-wise error rate accurately controlled at the desired level. We also present a sample size calculation method for designing microarray studies. Through simulations and data analyses, we find that the proposed methods for testing and sample size calculation are computationally fast and control error and power precisely.",
keywords = "Adjusted p-value, Bonferroni, Multi-step, Permutation, Simulation, Single-step",
author = "Jung, {Sin Ho} and Heejung Bang and Stanley Young",
year = "2005",
doi = "10.1093/biostatistics/kxh026",
language = "English (US)",
volume = "6",
pages = "157--169",
journal = "Biostatistics",
issn = "1465-4644",
publisher = "Oxford University Press",
number = "1",

}

TY - JOUR

T1 - Sample size calculation for multiple testing in microarray data analysis

AU - Jung, Sin Ho

AU - Bang, Heejung

AU - Young, Stanley

PY - 2005

Y1 - 2005

N2 - Microarray technology is rapidly emerging for genome-wide screening of differentially expressed genes between clinical subtypes or different conditions of human diseases. Traditional statistical testing approaches, such as the two-sample t-test or Wilcoxon test, are frequently used for evaluating statistical significance of informative expressions but require adjustment for large-scale multiplicity. Due to its simplicity, Bonferroni adjustment has been widely used to circumvent this problem. It is well known, however, that the standard Bonferroni test is often very conservative. In the present paper, we compare three multiple testing procedures in the microarray context: the original Bonferroni method, a Bonferroni-type improved single-step method and a step-down method. The latter two methods are based on nonparametric resampling, by which the null distribution can be derived with the dependency structure among gene expressions preserved and the family-wise error rate accurately controlled at the desired level. We also present a sample size calculation method for designing microarray studies. Through simulations and data analyses, we find that the proposed methods for testing and sample size calculation are computationally fast and control error and power precisely.

AB - Microarray technology is rapidly emerging for genome-wide screening of differentially expressed genes between clinical subtypes or different conditions of human diseases. Traditional statistical testing approaches, such as the two-sample t-test or Wilcoxon test, are frequently used for evaluating statistical significance of informative expressions but require adjustment for large-scale multiplicity. Due to its simplicity, Bonferroni adjustment has been widely used to circumvent this problem. It is well known, however, that the standard Bonferroni test is often very conservative. In the present paper, we compare three multiple testing procedures in the microarray context: the original Bonferroni method, a Bonferroni-type improved single-step method and a step-down method. The latter two methods are based on nonparametric resampling, by which the null distribution can be derived with the dependency structure among gene expressions preserved and the family-wise error rate accurately controlled at the desired level. We also present a sample size calculation method for designing microarray studies. Through simulations and data analyses, we find that the proposed methods for testing and sample size calculation are computationally fast and control error and power precisely.

KW - Adjusted p-value

KW - Bonferroni

KW - Multi-step

KW - Permutation

KW - Simulation

KW - Single-step

UR - http://www.scopus.com/inward/record.url?scp=21644451292&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=21644451292&partnerID=8YFLogxK

U2 - 10.1093/biostatistics/kxh026

DO - 10.1093/biostatistics/kxh026

M3 - Article

C2 - 15618534

AN - SCOPUS:21644451292

VL - 6

SP - 157

EP - 169

JO - Biostatistics

JF - Biostatistics

SN - 1465-4644

IS - 1

ER -