Choosing profile double-sampling designs for survival estimation with application to president's emergency plan for aids relief evaluation

Ming Wen An, Constantine E. Frangakis, Constantin Yiannoutsos

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Most studies that follow subjects over time are challenged by having some subjects who dropout. Double sampling is a design that selects and devotes resources to intensively pursue and find a subset of these dropouts, then uses data obtained from these to adjust naïve estimates, which are potentially biased by the dropout. Existing methods to estimate survival from double sampling assume a random sample. In limited-resource settings, however, generating accurate estimates using a minimum of resources is important. We propose using double-sampling designs that oversample certain profiles of dropouts as more efficient alternatives to random designs. First, we develop a framework to estimate the survival function under these profile double-sampling designs. We then derive the precision of these designs as a function of the rule for selecting different profiles, in order to identify more efficient designs. We illustrate using data from the United States President's Emergency Plan for AIDS Relief-funded HIV care and treatment program in western Kenya. Our results show why and how more efficient designs should oversample patients with shorter dropout times. Further, our work suggests generalizable practice for more efficient double-sampling designs, which can help maximize efficiency in resource-limited settings.

Original languageEnglish
Pages (from-to)2017-2029
Number of pages13
JournalStatistics in Medicine
Volume33
Issue number12
DOIs
StatePublished - May 30 2014

Fingerprint

Double Sampling
Sampling Design
Drop out
Emergency
Emergencies
Survival
Kenya
Evaluation
Resources
Acquired Immunodeficiency Syndrome
Estimate
HIV
Random Design
Survival Function
Biased
Maximise
Profile
Therapeutics
Subset
Design

Keywords

  • Covariates
  • Double sampling
  • Dropouts
  • HIV
  • Loss to follow-up
  • PEPFAR
  • Potential outcomes
  • Profile sampling
  • Survival

ASJC Scopus subject areas

  • Epidemiology
  • Statistics and Probability
  • Medicine(all)

Cite this

Choosing profile double-sampling designs for survival estimation with application to president's emergency plan for aids relief evaluation. / An, Ming Wen; Frangakis, Constantine E.; Yiannoutsos, Constantin.

In: Statistics in Medicine, Vol. 33, No. 12, 30.05.2014, p. 2017-2029.

Research output: Contribution to journalArticle

@article{9abda06a4e104004a19f83cf689385b8,
title = "Choosing profile double-sampling designs for survival estimation with application to president's emergency plan for aids relief evaluation",
abstract = "Most studies that follow subjects over time are challenged by having some subjects who dropout. Double sampling is a design that selects and devotes resources to intensively pursue and find a subset of these dropouts, then uses data obtained from these to adjust na{\"i}ve estimates, which are potentially biased by the dropout. Existing methods to estimate survival from double sampling assume a random sample. In limited-resource settings, however, generating accurate estimates using a minimum of resources is important. We propose using double-sampling designs that oversample certain profiles of dropouts as more efficient alternatives to random designs. First, we develop a framework to estimate the survival function under these profile double-sampling designs. We then derive the precision of these designs as a function of the rule for selecting different profiles, in order to identify more efficient designs. We illustrate using data from the United States President's Emergency Plan for AIDS Relief-funded HIV care and treatment program in western Kenya. Our results show why and how more efficient designs should oversample patients with shorter dropout times. Further, our work suggests generalizable practice for more efficient double-sampling designs, which can help maximize efficiency in resource-limited settings.",
keywords = "Covariates, Double sampling, Dropouts, HIV, Loss to follow-up, PEPFAR, Potential outcomes, Profile sampling, Survival",
author = "An, {Ming Wen} and Frangakis, {Constantine E.} and Constantin Yiannoutsos",
year = "2014",
month = "5",
day = "30",
doi = "10.1002/sim.6087",
language = "English",
volume = "33",
pages = "2017--2029",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "12",

}

TY - JOUR

T1 - Choosing profile double-sampling designs for survival estimation with application to president's emergency plan for aids relief evaluation

AU - An, Ming Wen

AU - Frangakis, Constantine E.

AU - Yiannoutsos, Constantin

PY - 2014/5/30

Y1 - 2014/5/30

N2 - Most studies that follow subjects over time are challenged by having some subjects who dropout. Double sampling is a design that selects and devotes resources to intensively pursue and find a subset of these dropouts, then uses data obtained from these to adjust naïve estimates, which are potentially biased by the dropout. Existing methods to estimate survival from double sampling assume a random sample. In limited-resource settings, however, generating accurate estimates using a minimum of resources is important. We propose using double-sampling designs that oversample certain profiles of dropouts as more efficient alternatives to random designs. First, we develop a framework to estimate the survival function under these profile double-sampling designs. We then derive the precision of these designs as a function of the rule for selecting different profiles, in order to identify more efficient designs. We illustrate using data from the United States President's Emergency Plan for AIDS Relief-funded HIV care and treatment program in western Kenya. Our results show why and how more efficient designs should oversample patients with shorter dropout times. Further, our work suggests generalizable practice for more efficient double-sampling designs, which can help maximize efficiency in resource-limited settings.

AB - Most studies that follow subjects over time are challenged by having some subjects who dropout. Double sampling is a design that selects and devotes resources to intensively pursue and find a subset of these dropouts, then uses data obtained from these to adjust naïve estimates, which are potentially biased by the dropout. Existing methods to estimate survival from double sampling assume a random sample. In limited-resource settings, however, generating accurate estimates using a minimum of resources is important. We propose using double-sampling designs that oversample certain profiles of dropouts as more efficient alternatives to random designs. First, we develop a framework to estimate the survival function under these profile double-sampling designs. We then derive the precision of these designs as a function of the rule for selecting different profiles, in order to identify more efficient designs. We illustrate using data from the United States President's Emergency Plan for AIDS Relief-funded HIV care and treatment program in western Kenya. Our results show why and how more efficient designs should oversample patients with shorter dropout times. Further, our work suggests generalizable practice for more efficient double-sampling designs, which can help maximize efficiency in resource-limited settings.

KW - Covariates

KW - Double sampling

KW - Dropouts

KW - HIV

KW - Loss to follow-up

KW - PEPFAR

KW - Potential outcomes

KW - Profile sampling

KW - Survival

UR - http://www.scopus.com/inward/record.url?scp=84899906147&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84899906147&partnerID=8YFLogxK

U2 - 10.1002/sim.6087

DO - 10.1002/sim.6087

M3 - Article

C2 - 24408038

AN - SCOPUS:84899906147

VL - 33

SP - 2017

EP - 2029

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 12

ER -