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

The Knox method and other tests for space-time interaction.

M Kulldorff1, U Hjalmars

  • 1Biometry Branch, DCP, National Cancer Institute, Bethesda, Maryland 20892-7354, USA. martinlink@neuron.uchc.edu

Biometrics
|April 25, 2001
PubMed
Summary

Geographical population shifts bias space-time interaction tests like the Knox test. This study quantifies this bias and introduces a Monte Carlo method for unbiased testing, improving future epidemiological study designs.

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

Continuous versus group sequential analysis for post-market drug and vaccine safety surveillance.

Biometrics·2015
Same author

Power Evaluation of Focused Cluster Tests.

Environmental and ecological statistics·2014
Same author

Automated use of WHONET and SaTScan to detect outbreaks of Shigella spp. using antimicrobial resistance phenotypes.

Epidemiology and infection·2009
Same author

Using encounters versus episodes in syndromic surveillance.

Journal of public health (Oxford, England)·2009
Same author

Geographic assessment of breast cancer screening by towns, zip codes, and census tracts.

Journal of public health management and practice : JPHMP·2007
Same author

Ambulatory-care diagnoses as potential indicators of outbreaks of gastrointestinal illness--Minnesota.

MMWR supplements·2005

Area of Science:

  • Epidemiology
  • Spatial Statistics
  • Biostatistics

Background:

  • Space-time interaction tests are crucial for identifying disease clusters.
  • The Knox method is a widely used test for space-time disease patterns.
  • Geographical population shifts can introduce bias into these tests.

Purpose of the Study:

  • To investigate the bias in the Knox test caused by geographical population shifts.
  • To propose and illustrate a method for constructing unbiased space-time interaction tests.

Main Methods:

  • Quantification of population shift bias in the Knox test.
  • Development of a Monte Carlo simulation method for unbiased testing.
  • Application of the method to the Knox test and a combined Knox test.

Related Experiment Videos

Main Results:

  • Population shifts can significantly bias space-time interaction test results.
  • The proposed Monte Carlo method effectively corrects for this bias.
  • Unbiased tests were successfully constructed for the Knox and combined Knox tests.

Conclusions:

  • The Knox method and similar tests are susceptible to bias from population redistribution.
  • A novel Monte Carlo approach provides a robust solution for unbiased space-time analysis.
  • Findings have direct implications for re-interpreting past research and designing future spatial epidemiological studies.