Perils and potentials of self-selected entry to epidemiological studies and surveys

Niels Keiding, Thomas Louis

Research output: Contribution to journalArticle

Abstract

Summary: Low front-end cost and rapid accrual make Web-based surveys and enrolment in studies attractive, but participants are often self-selected with little reference to a well-defined study base. Of course, high quality studies must be internally valid (validity of inferences for the sample at hand), but Web-based enrolment reactivates discussion of external validity (generalization of within-study inferences to a target population or context) in epidemiology and clinical trials. Survey research relies on a representative sample produced by a sampling frame, prespecified sampling process and weighting that maps results to an intended population. In contrast, recent analytical epidemiology has shifted the focus away from survey-type representativity to internal validity in the sample. Against this background, it is a good time for statisticians to take stock of our role and position regarding surveys, observational research in epidemiology and clinical studies. The central issue is whether conditional effects in the sample (the study population) may be transported to desired target populations. Success depends on compatibility of causal structures in study and target populations, and will require subject matter considerations in each concrete case. Statisticians, epidemiologists and survey researchers should work together to increase understanding of these challenges and to develop improved tools to handle them.

Original languageEnglish (US)
Pages (from-to)319-376
Number of pages58
JournalJournal of the Royal Statistical Society. Series A: Statistics in Society
Volume179
Issue number2
DOIs
StatePublished - Feb 1 2016

Fingerprint

Epidemiology
epidemiology
statistician
survey research
Web-based
Target
representativity
weighting
Clinical Trials
Compatibility
Weighting
Well-defined
Valid
Internal
Costs
costs
Inference
Sampling
Enrollment

Keywords

  • External validity
  • Internal validity, Non-probability samples
  • Representativity
  • Transportability
  • Unmeasured confounders
  • Web-based enrolment

ASJC Scopus subject areas

  • Statistics and Probability
  • Social Sciences (miscellaneous)
  • Economics and Econometrics
  • Statistics, Probability and Uncertainty

Cite this

Perils and potentials of self-selected entry to epidemiological studies and surveys. / Keiding, Niels; Louis, Thomas.

In: Journal of the Royal Statistical Society. Series A: Statistics in Society, Vol. 179, No. 2, 01.02.2016, p. 319-376.

Research output: Contribution to journalArticle

@article{4e23dd939cd04135a37f2b0de8fb615e,
title = "Perils and potentials of self-selected entry to epidemiological studies and surveys",
abstract = "Summary: Low front-end cost and rapid accrual make Web-based surveys and enrolment in studies attractive, but participants are often self-selected with little reference to a well-defined study base. Of course, high quality studies must be internally valid (validity of inferences for the sample at hand), but Web-based enrolment reactivates discussion of external validity (generalization of within-study inferences to a target population or context) in epidemiology and clinical trials. Survey research relies on a representative sample produced by a sampling frame, prespecified sampling process and weighting that maps results to an intended population. In contrast, recent analytical epidemiology has shifted the focus away from survey-type representativity to internal validity in the sample. Against this background, it is a good time for statisticians to take stock of our role and position regarding surveys, observational research in epidemiology and clinical studies. The central issue is whether conditional effects in the sample (the study population) may be transported to desired target populations. Success depends on compatibility of causal structures in study and target populations, and will require subject matter considerations in each concrete case. Statisticians, epidemiologists and survey researchers should work together to increase understanding of these challenges and to develop improved tools to handle them.",
keywords = "External validity, Internal validity, Non-probability samples, Representativity, Transportability, Unmeasured confounders, Web-based enrolment",
author = "Niels Keiding and Thomas Louis",
year = "2016",
month = "2",
day = "1",
doi = "10.1111/rssa.12136",
language = "English (US)",
volume = "179",
pages = "319--376",
journal = "Journal of the Royal Statistical Society. Series A: Statistics in Society",
issn = "0964-1998",
publisher = "Wiley-Blackwell",
number = "2",

}

TY - JOUR

T1 - Perils and potentials of self-selected entry to epidemiological studies and surveys

AU - Keiding, Niels

AU - Louis, Thomas

PY - 2016/2/1

Y1 - 2016/2/1

N2 - Summary: Low front-end cost and rapid accrual make Web-based surveys and enrolment in studies attractive, but participants are often self-selected with little reference to a well-defined study base. Of course, high quality studies must be internally valid (validity of inferences for the sample at hand), but Web-based enrolment reactivates discussion of external validity (generalization of within-study inferences to a target population or context) in epidemiology and clinical trials. Survey research relies on a representative sample produced by a sampling frame, prespecified sampling process and weighting that maps results to an intended population. In contrast, recent analytical epidemiology has shifted the focus away from survey-type representativity to internal validity in the sample. Against this background, it is a good time for statisticians to take stock of our role and position regarding surveys, observational research in epidemiology and clinical studies. The central issue is whether conditional effects in the sample (the study population) may be transported to desired target populations. Success depends on compatibility of causal structures in study and target populations, and will require subject matter considerations in each concrete case. Statisticians, epidemiologists and survey researchers should work together to increase understanding of these challenges and to develop improved tools to handle them.

AB - Summary: Low front-end cost and rapid accrual make Web-based surveys and enrolment in studies attractive, but participants are often self-selected with little reference to a well-defined study base. Of course, high quality studies must be internally valid (validity of inferences for the sample at hand), but Web-based enrolment reactivates discussion of external validity (generalization of within-study inferences to a target population or context) in epidemiology and clinical trials. Survey research relies on a representative sample produced by a sampling frame, prespecified sampling process and weighting that maps results to an intended population. In contrast, recent analytical epidemiology has shifted the focus away from survey-type representativity to internal validity in the sample. Against this background, it is a good time for statisticians to take stock of our role and position regarding surveys, observational research in epidemiology and clinical studies. The central issue is whether conditional effects in the sample (the study population) may be transported to desired target populations. Success depends on compatibility of causal structures in study and target populations, and will require subject matter considerations in each concrete case. Statisticians, epidemiologists and survey researchers should work together to increase understanding of these challenges and to develop improved tools to handle them.

KW - External validity

KW - Internal validity, Non-probability samples

KW - Representativity

KW - Transportability

KW - Unmeasured confounders

KW - Web-based enrolment

UR - http://www.scopus.com/inward/record.url?scp=84955094814&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84955094814&partnerID=8YFLogxK

U2 - 10.1111/rssa.12136

DO - 10.1111/rssa.12136

M3 - Article

AN - SCOPUS:84955094814

VL - 179

SP - 319

EP - 376

JO - Journal of the Royal Statistical Society. Series A: Statistics in Society

JF - Journal of the Royal Statistical Society. Series A: Statistics in Society

SN - 0964-1998

IS - 2

ER -