A combined efficient design for biomarker data subject to a limit of detection due to measuring instrument sensitivity

Enrique F. Schisterman, Albert Vexler, Aijun Ye, Neil J. Perkins

Research output: Contribution to journalArticle

Abstract

Pooling specimens, a well-accepted sampling strategy in biomedical research, can be applied to reduce the cost of studying biomarkers. Even if the cost of a single assay is not a major restriction in evaluating biomarkers, pooling can be a powerful design that increases the efficiency of estimation based on data that is censored due to an instrument's lower limit of detection (LLOD). However, there are situations when the pooling design strongly aggravates the detection limit problem. To combine the benefits of pooled assays and individual assays, hybrid designs that involve taking a sample of both pooled and individual specimens have been proposed. We examine the efficiency of these hybrid designs in estimating parameters of two systems subject to a LLOD: (1) normally distributed biomarker with normally distributed measurement error and pooling error; (2) Gamma distributed biomarker with double exponentially distributed measurement error and pooling error. Three-assay design and two-assay design with replicates are applied to estimate the measurement and pooling error. The Maximum likelihood method is used to estimate the parameters. We found that the simple one-pool design, where all assays but one are random individuals and a single pooled assay includes the remaining specimens, under plausible conditions, is very efficient and can be recommended for practical use.

Original languageEnglish (US)
Pages (from-to)2651-2667
Number of pages17
JournalAnnals of Applied Statistics
Volume5
Issue number4
DOIs
StatePublished - Dec 2011
Externally publishedYes

Fingerprint

Measuring instruments
Biomarkers
Pooling
Assays
Measurement Error
Measurement errors
Pooling Designs
Sampling Strategy
Detection Limit
Maximum Likelihood Method
Costs
Estimate
Design
Maximum likelihood
Restriction
Sampling

Keywords

  • Cost-efficient design
  • Duplicate
  • Limit of detection
  • Measurement error
  • One-pool design
  • Pooling
  • Three-assay design
  • Two-assay design

ASJC Scopus subject areas

  • Statistics, Probability and Uncertainty
  • Modeling and Simulation
  • Statistics and Probability

Cite this

A combined efficient design for biomarker data subject to a limit of detection due to measuring instrument sensitivity. / Schisterman, Enrique F.; Vexler, Albert; Ye, Aijun; Perkins, Neil J.

In: Annals of Applied Statistics, Vol. 5, No. 4, 12.2011, p. 2651-2667.

Research output: Contribution to journalArticle

Schisterman, Enrique F. ; Vexler, Albert ; Ye, Aijun ; Perkins, Neil J. / A combined efficient design for biomarker data subject to a limit of detection due to measuring instrument sensitivity. In: Annals of Applied Statistics. 2011 ; Vol. 5, No. 4. pp. 2651-2667.
@article{34a7b409cf8e49a2ae8be2a21c3eacef,
title = "A combined efficient design for biomarker data subject to a limit of detection due to measuring instrument sensitivity",
abstract = "Pooling specimens, a well-accepted sampling strategy in biomedical research, can be applied to reduce the cost of studying biomarkers. Even if the cost of a single assay is not a major restriction in evaluating biomarkers, pooling can be a powerful design that increases the efficiency of estimation based on data that is censored due to an instrument's lower limit of detection (LLOD). However, there are situations when the pooling design strongly aggravates the detection limit problem. To combine the benefits of pooled assays and individual assays, hybrid designs that involve taking a sample of both pooled and individual specimens have been proposed. We examine the efficiency of these hybrid designs in estimating parameters of two systems subject to a LLOD: (1) normally distributed biomarker with normally distributed measurement error and pooling error; (2) Gamma distributed biomarker with double exponentially distributed measurement error and pooling error. Three-assay design and two-assay design with replicates are applied to estimate the measurement and pooling error. The Maximum likelihood method is used to estimate the parameters. We found that the simple one-pool design, where all assays but one are random individuals and a single pooled assay includes the remaining specimens, under plausible conditions, is very efficient and can be recommended for practical use.",
keywords = "Cost-efficient design, Duplicate, Limit of detection, Measurement error, One-pool design, Pooling, Three-assay design, Two-assay design",
author = "Schisterman, {Enrique F.} and Albert Vexler and Aijun Ye and Perkins, {Neil J.}",
year = "2011",
month = "12",
doi = "10.1214/11-AOAS490",
language = "English (US)",
volume = "5",
pages = "2651--2667",
journal = "Annals of Applied Statistics",
issn = "1932-6157",
publisher = "Institute of Mathematical Statistics",
number = "4",

}

TY - JOUR

T1 - A combined efficient design for biomarker data subject to a limit of detection due to measuring instrument sensitivity

AU - Schisterman, Enrique F.

AU - Vexler, Albert

AU - Ye, Aijun

AU - Perkins, Neil J.

PY - 2011/12

Y1 - 2011/12

N2 - Pooling specimens, a well-accepted sampling strategy in biomedical research, can be applied to reduce the cost of studying biomarkers. Even if the cost of a single assay is not a major restriction in evaluating biomarkers, pooling can be a powerful design that increases the efficiency of estimation based on data that is censored due to an instrument's lower limit of detection (LLOD). However, there are situations when the pooling design strongly aggravates the detection limit problem. To combine the benefits of pooled assays and individual assays, hybrid designs that involve taking a sample of both pooled and individual specimens have been proposed. We examine the efficiency of these hybrid designs in estimating parameters of two systems subject to a LLOD: (1) normally distributed biomarker with normally distributed measurement error and pooling error; (2) Gamma distributed biomarker with double exponentially distributed measurement error and pooling error. Three-assay design and two-assay design with replicates are applied to estimate the measurement and pooling error. The Maximum likelihood method is used to estimate the parameters. We found that the simple one-pool design, where all assays but one are random individuals and a single pooled assay includes the remaining specimens, under plausible conditions, is very efficient and can be recommended for practical use.

AB - Pooling specimens, a well-accepted sampling strategy in biomedical research, can be applied to reduce the cost of studying biomarkers. Even if the cost of a single assay is not a major restriction in evaluating biomarkers, pooling can be a powerful design that increases the efficiency of estimation based on data that is censored due to an instrument's lower limit of detection (LLOD). However, there are situations when the pooling design strongly aggravates the detection limit problem. To combine the benefits of pooled assays and individual assays, hybrid designs that involve taking a sample of both pooled and individual specimens have been proposed. We examine the efficiency of these hybrid designs in estimating parameters of two systems subject to a LLOD: (1) normally distributed biomarker with normally distributed measurement error and pooling error; (2) Gamma distributed biomarker with double exponentially distributed measurement error and pooling error. Three-assay design and two-assay design with replicates are applied to estimate the measurement and pooling error. The Maximum likelihood method is used to estimate the parameters. We found that the simple one-pool design, where all assays but one are random individuals and a single pooled assay includes the remaining specimens, under plausible conditions, is very efficient and can be recommended for practical use.

KW - Cost-efficient design

KW - Duplicate

KW - Limit of detection

KW - Measurement error

KW - One-pool design

KW - Pooling

KW - Three-assay design

KW - Two-assay design

UR - http://www.scopus.com/inward/record.url?scp=84870269159&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84870269159&partnerID=8YFLogxK

U2 - 10.1214/11-AOAS490

DO - 10.1214/11-AOAS490

M3 - Article

AN - SCOPUS:84870269159

VL - 5

SP - 2651

EP - 2667

JO - Annals of Applied Statistics

JF - Annals of Applied Statistics

SN - 1932-6157

IS - 4

ER -