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

Residual plots for log odds ratio regression models.

M Tsujitani1, G G Koch

  • 1Department of Literature, Kobe Women's University, Hyogo, Japan.

Biometrics
|September 1, 1991
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

Geosmin-producing Species of Coelosphaerium (Synechococcales, Cyanobacteria) in Lake Shinji, Japan.

Scientific reports·2017
Same author

One in four people may develop symptomatic hip osteoarthritis in his or her lifetime.

Osteoarthritis and cartilage·2010
Same author

Neural discriminant analysis.

IEEE transactions on neural networks·2008
Same author

Predictive tests for linked changes.

Statistics in medicine·2008
Same author

Design of vaccine equivalence/non-inferiority trials with correlated multiple binomial endpoints.

Journal of biopharmaceutical statistics·2006
Same author

Are American College of Rheumatology 50% response criteria superior to 20% criteria in distinguishing active aggressive treatment in rheumatoid arthritis clinical trials reported since 1997? A meta-analysis of discriminant capacities.

Annals of the rheumatic diseases·2006

This study introduces graphical diagnostic methods using residual plots for log odds ratio regression models. These techniques help assess covariate effects, identify model issues like nonlinearity, and determine appropriate variable transformations for better analysis.

Area of Science:

  • Biostatistics
  • Statistical modeling
  • Data analysis

Background:

  • Log odds ratio regression models are crucial in statistical analysis, particularly for binary outcomes.
  • Assessing the impact of covariates and model fit is essential for reliable results.
  • Existing diagnostic methods may not fully capture complex covariate effects or model nonlinearities.

Purpose of the Study:

  • To present novel graphical diagnostic methods for log odds ratio regression.
  • To evaluate the utility of three specific residual plots in assessing covariate effects.
  • To demonstrate the application of these plots in identifying model misspecification and guiding variable transformation.

Main Methods:

  • Development and application of three residual plots: added variable plot, partial residual plot, and augmented partial residual plot.

Related Experiment Videos

  • Utilizing weighted least squares (WLS) as the underlying estimation method.
  • Analysis of a case-control study dataset to illustrate the practical use of the proposed plots.

    • Main Results:

    • The proposed residual plots effectively identify heterogeneity of error variances, outliers, and nonlinearity in log odds ratio models.
    • These graphical tools aid in determining the appropriate form of covariate inclusion (linear vs. nonlinear transformations).
    • The analysis of the case-control data demonstrated the practical utility of these diagnostic procedures.

    Conclusions:

    • Graphical diagnostic methods based on residual plots offer valuable insights into log odds ratio regression models.
    • These methods enhance the ability to detect model deficiencies and improve covariate effect assessment.
    • The presented techniques are particularly useful for model building and refinement in various statistical applications.