Quasi-experimental study designs series—paper 10: synthesizing evidence for effects collected from quasi-experimental studies presents surmountable challenges

Betsy Jane Becker; Ariel M Aloe; Maren Duvendack; T.D Stanley; Jeffrey C Valentine; Atle Fretheim; Peter Tugwell

doi:10.1016/j.jclinepi.2017.02.014

Back

Quasi-experimental study designs series—paper 10: synthesizing evidence for effects collected from quasi-experimental studies presents surmountable challenges

Journal article

Peer reviewed

Quasi-experimental study designs series—paper 10: synthesizing evidence for effects collected from quasi-experimental studies presents surmountable challenges

Betsy Jane Becker, Ariel M Aloe, Maren Duvendack, T.D Stanley, Jeffrey C Valentine, Atle Fretheim and Peter Tugwell

Journal of clinical epidemiology, Vol.89, pp.84-91

09/2017

DOI: 10.1016/j.jclinepi.2017.02.014

PMID: 28365308

Files and links (1)

url

https://ueaeprints.uea.ac.uk/id/eprint/63170/1/Accepted_manuscript.pdfView

Open Access

Abstract

To outline issues of importance to analytic approaches to the synthesis of quasi-experiments (QEs) and to provide a statistical model for use in analysis. We drew on studies of statistics, epidemiology, and social-science methodology to outline methods for synthesis of QE studies. The design and conduct of QEs, effect sizes from QEs, and moderator variables for the analysis of those effect sizes were discussed. Biases, confounding, design complexities, and comparisons across designs offer serious challenges to syntheses of QEs. Key components of meta-analyses of QEs were identified, including the aspects of QE study design to be coded and analyzed. Of utmost importance are the design and statistical controls implemented in the QEs. Such controls and any potential sources of bias and confounding must be modeled in analyses, along with aspects of the interventions and populations studied. Because of such controls, effect sizes from QEs are more complex than those from randomized experiments. A statistical meta-regression model that incorporates important features of the QEs under review was presented. Meta-analyses of QEs provide particular challenges, but thorough coding of intervention characteristics and study methods, along with careful analysis, should allow for sound inferences.

Confounding

Quasi-experiment

Risk-of-bias

Moderator variables

Effect size

Meta-analysis

Details

Title: Subtitle: Quasi-experimental study designs series—paper 10: synthesizing evidence for effects collected from quasi-experimental studies presents surmountable challenges
Creators: Betsy Jane Becker - Educational Psychology and Learning Systems, College of Education, Florida State University, 3210D Stone Bldg, Tallahassee, FL 32306-4453, USA
Ariel M Aloe - Psychological and Quantitative Foundations, University of Iowa, 368 (South) Lindquist Center, Iowa City, IA 52242, USA
Maren Duvendack - University of East Anglia, Norwich Research Park, Norwich NR4 7TJ, UK
T.D Stanley - Department of Economics, Hendrix College, 1600 Washington St, Conway, AR 72032, USA
Jeffrey C Valentine - Counseling and Human Development, University of Louisville, 309 Porter Education Building, Louisville, KY 40292, USA
Atle Fretheim - Global Health Unit, Division for Health Services, Norwegian Institute of Public Health, PO Box 4404 Nydalen, 0403 Oslo, Norway
Peter Tugwell - Department of Medicine, University of Ottawa, 272 Stewart St., Ottawa, Ontario, Canada K1N6K4
Resource Type: Journal article
Publication Details: Journal of clinical epidemiology, Vol.89, pp.84-91
DOI: 10.1016/j.jclinepi.2017.02.014
PMID: 28365308
NLM abbreviation: J Clin Epidemiol
ISSN: 0895-4356
eISSN: 1878-5921
Publisher: Elsevier Inc
Language: English
Date published: 09/2017
Academic Unit: Psychological and Quantitative Foundations
Record Identifier: 9983993483802771

Metrics

12 Record Views

17 Times Cited - Web of Science