Fast approximation of small p‐values in permutation tests by partitioning the permutations

Fast approximation of small p‐values in permutation tests by partitioning the permutations Introduction and MotivationMany researchers in the life sciences use permutation tests, for example, to test for differential gene expression (Doerge and Churchill, ; Morley et al., ; Stranger et al., , ; Raj et al., ), and to analyze brain images (Nichols and Holmes, ; Bartra et al., ; Simpson et al., ). These tests are useful when the sample size is too small for large sample theory to apply, or when the distribution of the test statistic is analytically intractable. Permutation tests are also exact, meaning that they control the type I error rate exactly for finite sample size (Lehmann and Romano, ). However, permutation tests can be computationally intensive, especially when estimating small p‐values for many tests. In this article, we present computationally efficient methods for approximating small permutation p‐values (e.g., <10−6) for the difference and ratio of means in two‐sample tests, though we speculate that our methods will also work for other smooth function of the means.We denote the two groups of sample data as x=(x1,…,xnx)′ and y=(y1,…,yny)′, with respective sample sizes nx and ny. We denote the full data as z=(x′,y′)′, with total sample size N=nx+ny. Writing z=(z1,…,zN)′, we have that zi=xi,i=1,…,nx, and znx+j=yj,j=1,…,ny. In http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Biometrics Wiley

Fast approximation of small p‐values in permutation tests by partitioning the permutations

Loading next page...
 
/lp/wiley/fast-approximation-of-small-p-values-in-permutation-tests-by-H0I4SSLC69
Publisher
Wiley
Copyright
© 2018, The International Biometric Society
ISSN
0006-341X
eISSN
1541-0420
D.O.I.
10.1111/biom.12731
Publisher site
See Article on Publisher Site

Abstract

Introduction and MotivationMany researchers in the life sciences use permutation tests, for example, to test for differential gene expression (Doerge and Churchill, ; Morley et al., ; Stranger et al., , ; Raj et al., ), and to analyze brain images (Nichols and Holmes, ; Bartra et al., ; Simpson et al., ). These tests are useful when the sample size is too small for large sample theory to apply, or when the distribution of the test statistic is analytically intractable. Permutation tests are also exact, meaning that they control the type I error rate exactly for finite sample size (Lehmann and Romano, ). However, permutation tests can be computationally intensive, especially when estimating small p‐values for many tests. In this article, we present computationally efficient methods for approximating small permutation p‐values (e.g., <10−6) for the difference and ratio of means in two‐sample tests, though we speculate that our methods will also work for other smooth function of the means.We denote the two groups of sample data as x=(x1,…,xnx)′ and y=(y1,…,yny)′, with respective sample sizes nx and ny. We denote the full data as z=(x′,y′)′, with total sample size N=nx+ny. Writing z=(z1,…,zN)′, we have that zi=xi,i=1,…,nx, and znx+j=yj,j=1,…,ny. In

Journal

BiometricsWiley

Published: Jan 1, 2018

Keywords: ; ; ; ;

References

You’re reading a free preview. Subscribe to read the entire article.


DeepDyve is your
personal research library

It’s your single place to instantly
discover and read the research
that matters to you.

Enjoy affordable access to
over 18 million articles from more than
15,000 peer-reviewed journals.

All for just $49/month

Explore the DeepDyve Library

Search

Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly

Organize

Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place.

Access

Get unlimited, online access to over 18 million full-text articles from more than 15,000 scientific journals.

Your journals are on DeepDyve

Read from thousands of the leading scholarly journals from SpringerNature, Elsevier, Wiley-Blackwell, Oxford University Press and more.

All the latest content is available, no embargo periods.

See the journals in your area

DeepDyve

Freelancer

DeepDyve

Pro

Price

FREE

$49/month
$360/year

Save searches from
Google Scholar,
PubMed

Create lists to
organize your research

Export lists, citations

Read DeepDyve articles

Abstract access only

Unlimited access to over
18 million full-text articles

Print

20 pages / month

PDF Discount

20% off