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

Analyses of two-way chronic studies.

J J Chen1, R L Kodell

  • 1National Center for Toxicological Research, U.S. Food and Drug Administration, Jefferson, Arkansas 72079.

Biometrics
|September 1, 1987
PubMed
Summary

This study introduces a novel statistical method for analyzing chronic tumor data with two factors, like sex and dose. It addresses challenges with unequal sample sizes, improving the analysis of main and combined effects.

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

Changes in phagocytosis and expression of microglial cells in craniocerebral injury mice models.

Journal of biological regulators and homeostatic agents·2016
Same author

MRI differential diagnosis of suspected multiple sclerosis.

Clinical radiology·2016
Same author

Interactions between head motion and coil sensitivity in accelerated fMRI.

Journal of neuroscience methods·2016
Same author

Downregulation of YAP-dependent Nupr1 promotes tumor-repopulating cell growth in soft matrices.

Oncogenesis·2016
Same author

Identification and expression analysis of the sting gene, a sensor of viral DNA, in common carp Cyprinus carpio.

Journal of fish biology·2016
Same author

Changes and clinical significance of serum vaspin levels in patients with type 2 diabetes.

Genetics and molecular research : GMR·2015

Area of Science:

  • Toxicologic Pathology
  • Biostatistics
  • Cancer Research

Background:

  • Chronic studies often involve complex experimental designs with multiple factors (e.g., sex, dose).
  • Analyzing tumor data requires robust statistical methods that account for main and interaction effects.
  • Traditional log-rank statistics may yield inaccurate null distributions with unequal and disproportional cell counts.

Purpose of the Study:

  • To propose a statistical method for analyzing tumor data from chronic studies with two-factor experimental designs.
  • To address the limitations of standard log-rank statistics when dealing with unequal and disproportional cell counts.
  • To evaluate methods for testing main effects and combined (interaction) effects in tumor data analysis.

Main Methods:

  • A stratified log-rank statistic is presented for testing main effects (row or column).
  • Additive and multiplicative models are considered for combined effects under the proportional hazards model.
  • A conservative statistic is proposed for testing the additivity of row and column effects.
  • Simulation experiments were conducted to assess the null distribution of the combined-effect test statistic and its power.

Main Results:

  • The null distribution of the unstratified log-rank statistic deviates from a chi-square distribution with unequal, disproportional cell counts.
  • The proposed methods provide a framework for analyzing complex tumor data from chronic studies.
  • The study illustrates the procedure using mammary tumor data from a DMBA-induced mouse model.

Conclusions:

  • The developed statistical approach enhances the analysis of tumor data in chronic studies with multifactorial designs.
  • Accurate statistical inference is crucial, especially when experimental data exhibit unequal and disproportional cell sizes.
  • The findings contribute to more reliable interpretations of carcinogenicity studies.

Related Experiment Videos