Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Small group estimation for public health

R A Spasoff1, C J Strike, R C Nair

  • 1Community Health Research Unit, University of Ottawa, Ontario.

Canadian Journal of Public Health = Revue Canadienne De Sante Publique
|March 1, 1996
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Social work services in family practice.

Canadian family physician Medecin de famille canadien·2011
Same author

Assessing the quality of care in family physicians' practices.

Canadian family physician Medecin de famille canadien·2011
Same author

Patients' attitudes towards a rural health centre.

Canadian family physician Medecin de famille canadien·2010
Same author

Misuse of statistical terminology.

Canadian Medical Association journal·2010
Same author

Fetal macrosomia and adolescence obesity: results from a longitudinal cohort study.

International journal of obesity (2005)·2009
Same author

Combining social network analysis and cluster analysis to identify sexual network types.

International journal of STD & AIDS·2007

This study explored synthetic and regression estimation for health indicators in small populations. Regression methods showed better accuracy than synthetic ones, though both had limitations for public health use.

Area of Science:

  • Public Health
  • Biostatistics
  • Epidemiology

Background:

  • Estimating health indicators in small populations is challenging due to data limitations.
  • Sociodemographic factors often correlate with health status, offering potential for indirect estimation.
  • The Ontario Health Survey (OHS) provides a benchmark for health data.

Purpose of the Study:

  • To evaluate synthetic and linear regression estimation techniques for health risk factors and indicators in small populations.
  • To compare the accuracy of these estimation methods against direct survey results (gold standards).
  • To assess the current utility and future potential of these statistical approaches for public health.

Main Methods:

  • Synthetic estimation based on population sociodemographics and OHS-derived variable relationships.

Related Experiment Videos

  • Linear regression modeling using sociodemographic and health variables from the OHS.
  • Validation of estimates by comparing them against direct OHS results.

    • Main Results:

    • Synthetic estimates exhibited lower dispersion compared to regression or direct OHS estimates.
    • Regression estimates generally outperformed synthetic estimates across most validation metrics.
    • Combined estimation approaches offered marginal improvements, but clear patterns were infrequent.
    • Despite high correlations ( > 0.8) for some variables, accuracy criteria were rarely met.

    Conclusions:

    • Current synthetic and regression estimation techniques have limited practical value for public health professionals.
    • Further research is warranted, particularly in developing combined synthetic and regression estimation approaches.
    • Improved statistical methods are needed for accurate health indicator estimation in small populations.