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

Misclassification of a prognostic dichotomous variable: sample size and parameter estimate adjustment

C J Tavaré1, E L Sobel, F H Gilles

  • 1Department of Preventive Medicine, USC School of Medicine, Los Angeles 90033, USA.

Statistics in Medicine
|June 30, 1995
PubMed
Summary

Measurement error in explanatory variables can reduce statistical power. This study shows asymptotic relative efficiency (ARE) equals the kappa statistic for dichotomous variables, enabling sample size adjustments without knowing true values.

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

Neonatal white matter damage and the fetal inflammatory response.

Seminars in fetal & neonatal medicine·2020
Same author

Abnormal cerebral microstructure in premature neonates with congenital heart disease.

AJNR. American journal of neuroradiology·2013
Same author

Abnormal microstructure of the atrophic thalamus in preterm survivors with periventricular leukomalacia.

AJNR. American journal of neuroradiology·2010
Same author

In utero eye development documented by fetal MR imaging.

AJNR. American journal of neuroradiology·2009
Same author

Quantitative short echo time 1H-MR spectroscopy of untreated pediatric brain tumors: preoperative diagnosis and characterization.

AJNR. American journal of neuroradiology·2006
Same author

Abducens length and vulnerability?

Neurology·2004

Area of Science:

  • Statistics
  • Biostatistics
  • Survival Analysis

Background:

  • Measurement error in explanatory variables affects statistical model efficiency.
  • Lagakos previously established asymptotic relative efficiency (ARE) as the squared correlation for linear, logistic, and proportional hazards models.
  • Estimating ARE often requires knowledge of the true correlation, which is frequently unavailable.

Purpose of the Study:

  • To determine the ARE for dichotomous explanatory variables with measurement error in specific statistical models.
  • To provide a method for sample size adjustment when true values are unobservable.
  • To develop an adjusted parameter estimate for proportional hazards survival models.

Main Methods:

  • Applied Lagakos's framework to dichotomous explanatory variables under a read-reread protocol.

Related Experiment Videos

  • Equated ARE with the kappa statistic for estimating measurement error.
  • Developed a heuristic adjustment for the beta parameter in proportional hazards models.

    • Main Results:

    • For dichotomous explanatory variables, the ARE equals the kappa statistic.
    • This allows for ARE estimation and sample size adjustment without knowing the true variable values.
    • An adjusted beta parameter estimate for survival models was developed.

    Conclusions:

    • The kappa statistic provides a practical method to estimate ARE and adjust sample size in the presence of measurement error for dichotomous variables.
    • This approach facilitates robust statistical analyses when true explanatory variable values cannot be ascertained.
    • The findings are applicable to epidemiological studies, such as those analyzing the Childhood Brain Tumour Consortium database.