LongCriLP: A test for bump hunting in longitudinal data

Jaroslaw Harezlak, Elena Naumova, Nan M. Laird

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

We propose an extension of the Harezlak and Heckman (J. Comput. Graph. Statist. 2001; 10(4): 713-729) test for detecting local extrema to the longitudinal data setting. We use penalized spline regression techniques (Statist. Sci. 1996; 11:89-102) to provide a computationally efficient method of testing for relatively large data sets. We estimate the p-values of our test, Long CriLP, with a smoothed bootstrap. Our simulation studies indicate that the test is generally conservative and has power exceeding 70 per cent at the α = 0.1 nominal level in most considered settings. Finally, we apply our testing procedure to the longitudinal measurements of body mass index of former prisoners of war in Vietnam and conclude that the mean population curve exhibits non-monotone behaviour.

Original languageEnglish (US)
Pages (from-to)1383-1397
Number of pages15
JournalStatistics in Medicine
Volume26
Issue number6
DOIs
StatePublished - Mar 15 2007
Externally publishedYes

Fingerprint

Longitudinal Data
Prisoners of War
Vietnam
Smoothed Bootstrap
Penalized Splines
Testing
Body Mass Index
p-Value
Extremum
Large Data Sets
Categorical or nominal
Regression
Simulation Study
Population
Curve
Graph in graph theory
Estimate
Datasets

Keywords

  • Body mass index
  • Bootstrap
  • Critical smoothing parameter
  • Longitudinal data
  • Penalized regression splines
  • Prisoners of war

ASJC Scopus subject areas

  • Epidemiology

Cite this

LongCriLP : A test for bump hunting in longitudinal data. / Harezlak, Jaroslaw; Naumova, Elena; Laird, Nan M.

In: Statistics in Medicine, Vol. 26, No. 6, 15.03.2007, p. 1383-1397.

Research output: Contribution to journalArticle

Harezlak, Jaroslaw ; Naumova, Elena ; Laird, Nan M. / LongCriLP : A test for bump hunting in longitudinal data. In: Statistics in Medicine. 2007 ; Vol. 26, No. 6. pp. 1383-1397.
@article{a6a42686b00243a982ae6eadd410d391,
title = "LongCriLP: A test for bump hunting in longitudinal data",
abstract = "We propose an extension of the Harezlak and Heckman (J. Comput. Graph. Statist. 2001; 10(4): 713-729) test for detecting local extrema to the longitudinal data setting. We use penalized spline regression techniques (Statist. Sci. 1996; 11:89-102) to provide a computationally efficient method of testing for relatively large data sets. We estimate the p-values of our test, Long CriLP, with a smoothed bootstrap. Our simulation studies indicate that the test is generally conservative and has power exceeding 70 per cent at the α = 0.1 nominal level in most considered settings. Finally, we apply our testing procedure to the longitudinal measurements of body mass index of former prisoners of war in Vietnam and conclude that the mean population curve exhibits non-monotone behaviour.",
keywords = "Body mass index, Bootstrap, Critical smoothing parameter, Longitudinal data, Penalized regression splines, Prisoners of war",
author = "Jaroslaw Harezlak and Elena Naumova and Laird, {Nan M.}",
year = "2007",
month = "3",
day = "15",
doi = "10.1002/sim.2623",
language = "English (US)",
volume = "26",
pages = "1383--1397",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "6",

}

TY - JOUR

T1 - LongCriLP

T2 - A test for bump hunting in longitudinal data

AU - Harezlak, Jaroslaw

AU - Naumova, Elena

AU - Laird, Nan M.

PY - 2007/3/15

Y1 - 2007/3/15

N2 - We propose an extension of the Harezlak and Heckman (J. Comput. Graph. Statist. 2001; 10(4): 713-729) test for detecting local extrema to the longitudinal data setting. We use penalized spline regression techniques (Statist. Sci. 1996; 11:89-102) to provide a computationally efficient method of testing for relatively large data sets. We estimate the p-values of our test, Long CriLP, with a smoothed bootstrap. Our simulation studies indicate that the test is generally conservative and has power exceeding 70 per cent at the α = 0.1 nominal level in most considered settings. Finally, we apply our testing procedure to the longitudinal measurements of body mass index of former prisoners of war in Vietnam and conclude that the mean population curve exhibits non-monotone behaviour.

AB - We propose an extension of the Harezlak and Heckman (J. Comput. Graph. Statist. 2001; 10(4): 713-729) test for detecting local extrema to the longitudinal data setting. We use penalized spline regression techniques (Statist. Sci. 1996; 11:89-102) to provide a computationally efficient method of testing for relatively large data sets. We estimate the p-values of our test, Long CriLP, with a smoothed bootstrap. Our simulation studies indicate that the test is generally conservative and has power exceeding 70 per cent at the α = 0.1 nominal level in most considered settings. Finally, we apply our testing procedure to the longitudinal measurements of body mass index of former prisoners of war in Vietnam and conclude that the mean population curve exhibits non-monotone behaviour.

KW - Body mass index

KW - Bootstrap

KW - Critical smoothing parameter

KW - Longitudinal data

KW - Penalized regression splines

KW - Prisoners of war

UR - http://www.scopus.com/inward/record.url?scp=33847705313&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33847705313&partnerID=8YFLogxK

U2 - 10.1002/sim.2623

DO - 10.1002/sim.2623

M3 - Article

C2 - 16850452

AN - SCOPUS:33847705313

VL - 26

SP - 1383

EP - 1397

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 6

ER -