Methods and Risks of Bias in Natural Experiments in Obesity: Opportunities for the Future Informed by a Systematic Review

Research output: Contribution to journalReview article

Abstract

Objective: This paper promotes rigorous methods and designs currently underutilized in obesity research, informed by a recent systematic review of the methods and risks of bias in studies of policies, programs, and built environment changes for obesity prevention and control. Methods: To determine the current state of the field, relevant databases from 2000 to 2017 were searched to identify studies that fit the inclusion criteria. Study design, analytic approach, and other details of study methods were abstracted. These findings inform recommendations for obesity researchers and the field as a whole. Results: Previously identified were 156 natural experiment studies. Most were cross-sectional (35%), pre-post single group comparison (31%), or difference-in-differences designs (29%). Few used rigorous causal designs such as interrupted time series with more than two time points, propensity score methods, or instrumental variables. The potential relevance for obesity research is discussed, and recommendations for obesity researchers are provided. Conclusions: To strengthen natural experiment study designs and enhance the validity of results, researchers should carefully consider and control for confounding and selection of comparison groups and consider study designs that address these biases.

Original languageEnglish (US)
Pages (from-to)1950-1957
Number of pages8
JournalObesity
Volume27
Issue number12
DOIs
StatePublished - Dec 1 2019

Fingerprint

Obesity
Research Personnel
Propensity Score
Research
Reproducibility of Results
Databases

ASJC Scopus subject areas

  • Medicine (miscellaneous)
  • Endocrinology, Diabetes and Metabolism
  • Endocrinology
  • Nutrition and Dietetics

Cite this

@article{db7ec75b2f99422a8d541d120799b5ad,
title = "Methods and Risks of Bias in Natural Experiments in Obesity: Opportunities for the Future Informed by a Systematic Review",
abstract = "Objective: This paper promotes rigorous methods and designs currently underutilized in obesity research, informed by a recent systematic review of the methods and risks of bias in studies of policies, programs, and built environment changes for obesity prevention and control. Methods: To determine the current state of the field, relevant databases from 2000 to 2017 were searched to identify studies that fit the inclusion criteria. Study design, analytic approach, and other details of study methods were abstracted. These findings inform recommendations for obesity researchers and the field as a whole. Results: Previously identified were 156 natural experiment studies. Most were cross-sectional (35{\%}), pre-post single group comparison (31{\%}), or difference-in-differences designs (29{\%}). Few used rigorous causal designs such as interrupted time series with more than two time points, propensity score methods, or instrumental variables. The potential relevance for obesity research is discussed, and recommendations for obesity researchers are provided. Conclusions: To strengthen natural experiment study designs and enhance the validity of results, researchers should carefully consider and control for confounding and selection of comparison groups and consider study designs that address these biases.",
author = "Knapp, {Emily A.} and Bennett, {Wendy L.} and Wilson, {Renee F.} and Allen Zhang and Eva Tseng and Cheskin, {Lawrence J.} and Bass, {Eric B.} and Hadi Kharrazi and Stuart, {Elizabeth A.}",
year = "2019",
month = "12",
day = "1",
doi = "10.1002/oby.22645",
language = "English (US)",
volume = "27",
pages = "1950--1957",
journal = "Obesity",
issn = "1930-7381",
publisher = "Wiley-Blackwell",
number = "12",

}

TY - JOUR

T1 - Methods and Risks of Bias in Natural Experiments in Obesity

T2 - Opportunities for the Future Informed by a Systematic Review

AU - Knapp, Emily A.

AU - Bennett, Wendy L.

AU - Wilson, Renee F.

AU - Zhang, Allen

AU - Tseng, Eva

AU - Cheskin, Lawrence J.

AU - Bass, Eric B.

AU - Kharrazi, Hadi

AU - Stuart, Elizabeth A.

PY - 2019/12/1

Y1 - 2019/12/1

N2 - Objective: This paper promotes rigorous methods and designs currently underutilized in obesity research, informed by a recent systematic review of the methods and risks of bias in studies of policies, programs, and built environment changes for obesity prevention and control. Methods: To determine the current state of the field, relevant databases from 2000 to 2017 were searched to identify studies that fit the inclusion criteria. Study design, analytic approach, and other details of study methods were abstracted. These findings inform recommendations for obesity researchers and the field as a whole. Results: Previously identified were 156 natural experiment studies. Most were cross-sectional (35%), pre-post single group comparison (31%), or difference-in-differences designs (29%). Few used rigorous causal designs such as interrupted time series with more than two time points, propensity score methods, or instrumental variables. The potential relevance for obesity research is discussed, and recommendations for obesity researchers are provided. Conclusions: To strengthen natural experiment study designs and enhance the validity of results, researchers should carefully consider and control for confounding and selection of comparison groups and consider study designs that address these biases.

AB - Objective: This paper promotes rigorous methods and designs currently underutilized in obesity research, informed by a recent systematic review of the methods and risks of bias in studies of policies, programs, and built environment changes for obesity prevention and control. Methods: To determine the current state of the field, relevant databases from 2000 to 2017 were searched to identify studies that fit the inclusion criteria. Study design, analytic approach, and other details of study methods were abstracted. These findings inform recommendations for obesity researchers and the field as a whole. Results: Previously identified were 156 natural experiment studies. Most were cross-sectional (35%), pre-post single group comparison (31%), or difference-in-differences designs (29%). Few used rigorous causal designs such as interrupted time series with more than two time points, propensity score methods, or instrumental variables. The potential relevance for obesity research is discussed, and recommendations for obesity researchers are provided. Conclusions: To strengthen natural experiment study designs and enhance the validity of results, researchers should carefully consider and control for confounding and selection of comparison groups and consider study designs that address these biases.

UR - http://www.scopus.com/inward/record.url?scp=85074834770&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074834770&partnerID=8YFLogxK

U2 - 10.1002/oby.22645

DO - 10.1002/oby.22645

M3 - Review article

C2 - 31693802

AN - SCOPUS:85074834770

VL - 27

SP - 1950

EP - 1957

JO - Obesity

JF - Obesity

SN - 1930-7381

IS - 12

ER -