Meta-analysis of survey data: application to health services research

  • Sowmya R. Rao
  • Barry I. Graubard
  • Christopher H. Schmid
  • Sally C. Morton
  • Thomas A. Louis
  • Alan M. Zaslavsky
  • Dianne M. Finkelstein
Article

DOI: 10.1007/s10742-008-0032-0

Cite this article as:
Rao, S.R., Graubard, B.I., Schmid, C.H. et al. Health Serv Outcomes Res Method (2008) 8: 98. doi:10.1007/s10742-008-0032-0

Abstract

Traditionally, meta-analysis methods have been developed and used to combine data from several independent clinical trials as well as observational studies, but have not been as widely used in survey research. This paper describes the steps in conducting such a meta-analysis of surveys, to obtain a single summary estimate from a combination of individual-level and summary data. The methods are applied in the context of a project aimed at obtaining an estimate of the prevalence of use of electronic health records.

Keywords

Meta-analysis Surveys Health research Electronic health record 

Copyright information

© Springer Science+Business Media, LLC 2008

Authors and Affiliations

  • Sowmya R. Rao
    • 1
  • Barry I. Graubard
    • 2
  • Christopher H. Schmid
    • 3
  • Sally C. Morton
    • 4
  • Thomas A. Louis
    • 5
  • Alan M. Zaslavsky
    • 6
  • Dianne M. Finkelstein
    • 7
  1. 1.MGH Biostatistics Center and The Institute for Health Policy, MGHBostonUSA
  2. 2.National Cancer InstituteBethesdaUSA
  3. 3.Tufts Sackler School of Graduate Biomedical SciencesBostonUSA
  4. 4.RTI InternationalResearch Triangle ParkUSA
  5. 5.Johns Hopkins Bloomberg School of Public HealthBaltimoreUSA
  6. 6.Department of Health Care PolicyHarvard Medical SchoolBostonUSA
  7. 7.MGH Biostatistics Center, MGHBostonUSA