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

Matrix methods for estimating odds ratios with misclassified exposure data: extensions and comparisons.

M J Morrissey1, D Spiegelman

  • 1Department of Biostatistics, Harvard School of Public Health, Boston, Massachusetts 02115, USA. mmorriss@hsph.harvard.edu

Biometrics
|April 25, 2001
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

Acceptability of Self-sampling in Human Papillomavirus Deoxyribonucleic acid based Cervical Screening in Nepal: A Mixed-Methods Study.

Kathmandu University medical journal (KUMJ)·2026
Same author

Universal test and treat in relation to HIV disease progression: results from a stepped-wedge trial in Eswatini.

HIV medicine·2020
Same author

Mortality under early access to antiretroviral therapy vs. Eswatini's national standard of care: the MaxART clustered randomized stepped-wedge trial.

HIV medicine·2020
Same author

On the analysis of two-phase designs in cluster-correlated data settings.

Statistics in medicine·2019
Same author

Substituting brown rice for white rice on diabetes risk factors in India: a randomised controlled trial.

The British journal of nutrition·2019
Same author

There is no impact of exposure measurement error on latency estimation in linear models.

Statistics in medicine·2018

The matrix and inverse matrix methods for correcting exposure misclassification bias were compared to the maximum likelihood estimator (MLE). The inverse matrix method showed higher efficiency under differential misclassification, while MLE was more efficient in other scenarios.

Area of Science:

  • Epidemiology
  • Biostatistics

Background:

  • Exposure misclassification is a significant challenge in epidemiologic research.
  • Accurate exposure assessment is crucial for valid study findings.

Purpose of the Study:

  • To compare the efficiency of the matrix method and the inverse matrix method against the maximum likelihood estimator (MLE) for correcting odds ratio bias.
  • To evaluate the performance of these methods under different misclassification assumptions (differential and nondifferential).

Main Methods:

  • The study employed simulation and analysis of real-world data to compare statistical methods.
  • Methods evaluated include the matrix method, inverse matrix method, and maximum likelihood estimation (MLE).
  • Efficiency was assessed using asymptotic relative efficiency (ARE) under varying parameters like sensitivity, specificity, and case-control ratios.

Related Experiment Videos

Main Results:

  • Under differential misclassification, the inverse matrix method consistently outperformed the matrix method.
  • The MLE demonstrated superior efficiency compared to the matrix method in both sudden infant death syndrome (SIDS) and breast cancer studies.
  • Efficiency of the matrix and inverse matrix methods is highly dependent on specific study parameters.

Conclusions:

  • The choice of method for correcting exposure misclassification bias is critical and depends on the nature of misclassification and study parameters.
  • Maximum likelihood estimation offers a robust approach for bias correction, particularly under nondifferential misclassification.
  • Further research into the performance of these methods across diverse epidemiologic contexts is warranted.