Related Experiment Videos
A hypothesis test for the end of a common source outbreak
1Department of Biostatistics, Johns Hopkins Bloomberg School of Public Health, Baltimore, Maryland 21205, USA. rbrook@jhsph.edu
Biometrics
|March 18, 2006
Summary
This study introduces a new method to determine when an infectious disease outbreak has ended, even without knowing exact exposure times or incubation periods. The procedure, based on disease onset dates, proves robust and minimally affected by multiple testing.
Area of Science:
- Epidemiology
- Biostatistics
- Public Health
Background:
- Common source outbreaks pose significant public health challenges.
- Determining the end of an outbreak is crucial for resource allocation and control measures.
- Existing methods may require knowledge of exposure dates or precise incubation period distributions, which are often unavailable.
Purpose of the Study:
- To develop a hypothesis-testing procedure for identifying the end of a common source outbreak.
- To address scenarios where exact exposure timing and incubation period distributions are unknown.
- To evaluate the robustness and error rates of the proposed method.
Main Methods:
- The procedure utilizes the spacings between ordered calendar dates of disease onset.
- A simulation study was conducted to assess method robustness across various incubation period models.
- Mathematical expressions for outbreak-wise type I error probability were derived.
Main Results:
- The hypothesis-testing procedure effectively determines outbreak cessation.
- The method demonstrates robustness against different incubation period distributions.
- Multiple testing was found to have a minimal impact on the overall type I error probability.
Conclusions:
- The developed statistical procedure offers a reliable tool for ending outbreak investigations.
- The findings are applicable to real-world scenarios, including the 2001 U.S. anthrax outbreak.
- The method provides a statistically sound approach when detailed epidemiological data is limited.