Semiparametric regression models for a right-skewed outcome subject to pooling

Emily M. Mitchell, Robert H. Lyles, Amita K. Manatunga, Enrique F. Schisterman

Research output: Contribution to journalArticle

Abstract

Pooling specimens prior to performing laboratory assays has various benefits. Pooling can help to reduce cost, preserve irreplaceable specimens, meet minimal volume requirements for certain lab tests, and even reduce information loss when a limit of detection is present. Regardless of the motivation for pooling, appropriate analytical techniques must be applied in order to obtain valid inference from composite specimens. When biomarkers are treated as the outcome in a regression model, techniques applicable to individually measured specimens may not be valid when measurements are taken from pooled specimens, particularly when the biomarker is positive and right skewed. In this paper, we propose a novel semiparametric estimation method based on an adaptation of the quasi-likelihood approach that can be applied to a right-skewed outcome subject to pooling. We use simulation studies to compare this method with an existing estimation technique that provides valid estimates only when pools are formed from specimens with identical predictor values. Simulation results and analysis of a motivating example demonstrate that, when appropriate estimation techniques are applied to strategically formed pools, valid and efficient estimation of the regression coefficients can be achieved.

Original languageEnglish (US)
Pages (from-to)541-548
Number of pages8
JournalAmerican Journal of Epidemiology
Volume181
Issue number7
DOIs
StatePublished - Apr 1 2015
Externally publishedYes

Fingerprint

Biomarkers
Limit of Detection
Costs and Cost Analysis

Keywords

  • biomarkers
  • design
  • pooled specimens
  • quasi-likelihood
  • skewness
  • statistical analysis

ASJC Scopus subject areas

  • Epidemiology

Cite this

Mitchell, E. M., Lyles, R. H., Manatunga, A. K., & Schisterman, E. F. (2015). Semiparametric regression models for a right-skewed outcome subject to pooling. American Journal of Epidemiology, 181(7), 541-548. https://doi.org/10.1093/aje/kwu301

Semiparametric regression models for a right-skewed outcome subject to pooling. / Mitchell, Emily M.; Lyles, Robert H.; Manatunga, Amita K.; Schisterman, Enrique F.

In: American Journal of Epidemiology, Vol. 181, No. 7, 01.04.2015, p. 541-548.

Research output: Contribution to journalArticle

Mitchell, EM, Lyles, RH, Manatunga, AK & Schisterman, EF 2015, 'Semiparametric regression models for a right-skewed outcome subject to pooling', American Journal of Epidemiology, vol. 181, no. 7, pp. 541-548. https://doi.org/10.1093/aje/kwu301
Mitchell, Emily M. ; Lyles, Robert H. ; Manatunga, Amita K. ; Schisterman, Enrique F. / Semiparametric regression models for a right-skewed outcome subject to pooling. In: American Journal of Epidemiology. 2015 ; Vol. 181, No. 7. pp. 541-548.
@article{1c60a3f6c2074887b15b6a89b3d26316,
title = "Semiparametric regression models for a right-skewed outcome subject to pooling",
abstract = "Pooling specimens prior to performing laboratory assays has various benefits. Pooling can help to reduce cost, preserve irreplaceable specimens, meet minimal volume requirements for certain lab tests, and even reduce information loss when a limit of detection is present. Regardless of the motivation for pooling, appropriate analytical techniques must be applied in order to obtain valid inference from composite specimens. When biomarkers are treated as the outcome in a regression model, techniques applicable to individually measured specimens may not be valid when measurements are taken from pooled specimens, particularly when the biomarker is positive and right skewed. In this paper, we propose a novel semiparametric estimation method based on an adaptation of the quasi-likelihood approach that can be applied to a right-skewed outcome subject to pooling. We use simulation studies to compare this method with an existing estimation technique that provides valid estimates only when pools are formed from specimens with identical predictor values. Simulation results and analysis of a motivating example demonstrate that, when appropriate estimation techniques are applied to strategically formed pools, valid and efficient estimation of the regression coefficients can be achieved.",
keywords = "biomarkers, design, pooled specimens, quasi-likelihood, skewness, statistical analysis",
author = "Mitchell, {Emily M.} and Lyles, {Robert H.} and Manatunga, {Amita K.} and Schisterman, {Enrique F.}",
year = "2015",
month = "4",
day = "1",
doi = "10.1093/aje/kwu301",
language = "English (US)",
volume = "181",
pages = "541--548",
journal = "American Journal of Epidemiology",
issn = "0002-9262",
publisher = "Oxford University Press",
number = "7",

}

TY - JOUR

T1 - Semiparametric regression models for a right-skewed outcome subject to pooling

AU - Mitchell, Emily M.

AU - Lyles, Robert H.

AU - Manatunga, Amita K.

AU - Schisterman, Enrique F.

PY - 2015/4/1

Y1 - 2015/4/1

N2 - Pooling specimens prior to performing laboratory assays has various benefits. Pooling can help to reduce cost, preserve irreplaceable specimens, meet minimal volume requirements for certain lab tests, and even reduce information loss when a limit of detection is present. Regardless of the motivation for pooling, appropriate analytical techniques must be applied in order to obtain valid inference from composite specimens. When biomarkers are treated as the outcome in a regression model, techniques applicable to individually measured specimens may not be valid when measurements are taken from pooled specimens, particularly when the biomarker is positive and right skewed. In this paper, we propose a novel semiparametric estimation method based on an adaptation of the quasi-likelihood approach that can be applied to a right-skewed outcome subject to pooling. We use simulation studies to compare this method with an existing estimation technique that provides valid estimates only when pools are formed from specimens with identical predictor values. Simulation results and analysis of a motivating example demonstrate that, when appropriate estimation techniques are applied to strategically formed pools, valid and efficient estimation of the regression coefficients can be achieved.

AB - Pooling specimens prior to performing laboratory assays has various benefits. Pooling can help to reduce cost, preserve irreplaceable specimens, meet minimal volume requirements for certain lab tests, and even reduce information loss when a limit of detection is present. Regardless of the motivation for pooling, appropriate analytical techniques must be applied in order to obtain valid inference from composite specimens. When biomarkers are treated as the outcome in a regression model, techniques applicable to individually measured specimens may not be valid when measurements are taken from pooled specimens, particularly when the biomarker is positive and right skewed. In this paper, we propose a novel semiparametric estimation method based on an adaptation of the quasi-likelihood approach that can be applied to a right-skewed outcome subject to pooling. We use simulation studies to compare this method with an existing estimation technique that provides valid estimates only when pools are formed from specimens with identical predictor values. Simulation results and analysis of a motivating example demonstrate that, when appropriate estimation techniques are applied to strategically formed pools, valid and efficient estimation of the regression coefficients can be achieved.

KW - biomarkers

KW - design

KW - pooled specimens

KW - quasi-likelihood

KW - skewness

KW - statistical analysis

UR - http://www.scopus.com/inward/record.url?scp=84926618705&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84926618705&partnerID=8YFLogxK

U2 - 10.1093/aje/kwu301

DO - 10.1093/aje/kwu301

M3 - Article

VL - 181

SP - 541

EP - 548

JO - American Journal of Epidemiology

JF - American Journal of Epidemiology

SN - 0002-9262

IS - 7

ER -