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

Classical statistical considerations in medical decision models.

R D Rifkin

    Medical Decision Making : an International Journal of the Society for Medical Decision Making
    |January 1, 1983
    PubMed
    Summary

    Sampling errors significantly impact decision-analytic models, potentially amplifying small data inaccuracies into large errors in predictions. This unreliability necessitates quantifying statistical error in all decision analyses for accurate 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

    Physiological basis of flow dependence of Gorlin formula valve area in aortic stenosis: analysis using an hydraulic model of pulsatile flow.

    The Journal of heart valve disease·2000
    Same author

    Echocardiography allows safer venous cannulation during excision of large right atrial masses.

    The Annals of thoracic surgery·1998
    Same author

    The influence of myocardial temperature on stunning following coronary revascularization.

    Annals of the New York Academy of Sciences·1996
    Same author

    Pacemaker lead infection: detection by multiplane transesophageal echocardiography.

    American heart journal·1996
    Same author

    Comparison of proximal isovelocity surface area method with pressure half-time and planimetry in evaluation of mitral stenosis.

    Journal of the American College of Cardiology·1995
    Same author

    Effects of correlated and uncorrelated measurement error on linear regression and correlation in medical method comparison studies.

    Statistics in medicine·1995

    Area of Science:

    • Decision Analysis
    • Biostatistics
    • Health Economics

    Background:

    • Decision-analytic models are crucial for clinical and health economic evaluations.
    • The reliability of these models depends on the accuracy of input data and statistical assumptions.
    • Understanding the propagation of sampling error is essential for robust model interpretation.

    Purpose of the Study:

    • To investigate the influence of sampling error on decision-analytic models.
    • To quantify how statistical errors in data affect model reliability, specifically the probability decision threshold and expected utility.
    • To assess the impact of compounded errors across multiple variables.

    Main Methods:

    • Development of formulas to link statistical error in data samples to errors in model outputs.

    Related Experiment Videos

  • Validation of these formulas using a simulation experiment.
  • Application of the validated formulas to a hypothetical decision model and a clinical scenario (appendicitis treatment).

    • Main Results:

    • Modest statistical errors in input variables can be amplified into substantial errors in the probability decision threshold and predicted gain in utility.
    • Simultaneous errors in multiple variables can compound, leading to unexpectedly large unreliability.
    • Model predictions can become unreliable across a wide range of disease probabilities due to error amplification.

    Conclusions:

    • Sampling error poses a significant threat to the reliability of decision-analytic models.
    • The interpretation of decision analysis results must consider both the predicted utility gain and a quantitative measure of prediction reliability.
    • Determining statistical error should be an integral part of any formal decision analysis to ensure accurate clinical and economic decision-making.