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

Methods of evaluation in outcomes research.

P J Reed1

  • 1Department of Pharmacy Practice and Pharmacoeconomics, University of Tennessee College of Pharmacy, Memphis 38163, USA.

The American Journal of Managed Care
|May 26, 1999
PubMed
Summary

This study explains advanced statistical methods for analyzing health status measurement tools, like the SF-36. It highlights why comparing mean scores can be misleading and introduces structural equation modeling for better data interpretation.

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

SF-36 as a predictor of health states.

Value in health : the journal of the International Society for Pharmacoeconomics and Outcomes Research·2006
Same author

Use of cloprostenol as an abortifacient in the llama (Lama glama).

Theriogenology·2000
Same author

Medical outcomes study short form 36: testing and cross-validating a second-order factorial structure for health system employees.

Health services research·1998
Same author

Blood mineral and vitamin E concentrations in llamas.

American journal of veterinary research·1998
Same author

Morphometric evaluation of growth in llamas (Lama glama) from birth to maturity.

Journal of the American Veterinary Medical Association·1992
Same author

Comparison of ionic and non-ionic contrast agents in cardiac catheterization: the effects of ventriculography and coronary arteriography on hemodynamics, electrocardiography, and serum creatinine.

Catheterization and cardiovascular diagnosis·1991

Area of Science:

  • Health outcomes research
  • Psychometrics
  • Statistical modeling

Background:

  • Interpreting humanistic outcomes from health status measurement tools requires careful statistical consideration.
  • Traditional methods like comparing mean scores may not be appropriate for complex data structures.
  • Health status measurement tools, such as the SF-36, often yield data requiring advanced analytical approaches.

Purpose of the Study:

  • To provide foundational knowledge on methods for evaluating invariant factorial structures in health status measurement tools.
  • To introduce alternative data evaluation methods beyond simple mean score comparisons.
  • To elucidate the utility of structural equation modeling (SEM) in analyzing data from instruments like the SF-36.

Main Methods:

  • Discussion of the limitations of mean score comparisons for humanistic outcomes.
  • Identification of alternative statistical methods for analyzing health status data.
  • Explanation of key psychometric concepts: validity, reliability, and structure.
  • Introduction to structural equation modeling (SEM) and its application to health status measurement tools.
  • Overview of statistical software utilized for SEM.

Main Results:

  • Mean score comparisons can be inappropriate for interpreting nuanced humanistic outcomes.
  • Alternative methods offer more robust analysis of health status data.
  • Understanding validity, reliability, and structure is crucial for appropriate tool selection and interpretation.
  • Structural equation modeling provides a powerful framework for analyzing complex relationships within health status data.
  • Specific statistical software facilitates the implementation of SEM.

Conclusions:

  • Advanced statistical methods, particularly structural equation modeling, are essential for accurate interpretation of health status measurement tools.
  • Healthcare professionals should be aware of the limitations of basic statistical approaches and explore more sophisticated techniques.
  • Proper application of psychometric principles and statistical modeling enhances the value derived from health status data.

Related Experiment Videos