Display Settings:

Format

Send to:

Choose Destination
    Epidemiol Perspect Innov. 2007 Feb 16;4:1.

    Applying the compound Poisson process model to the reporting of injury-related mortality rates.

    Source

    Office of Statistics and Programming, National Center for Injury Prevention and Control, Centers for Disease Control and Prevention, Atlanta, GA, USA. skegler@cdc.gov

    Abstract

    Injury-related mortality rate estimates are often analyzed under the assumption that case counts follow a Poisson distribution. Certain types of injury incidents occasionally involve multiple fatalities, however, resulting in dependencies between cases that are not reflected in the simple Poisson model and which can affect even basic statistical analyses. This paper explores the compound Poisson process model as an alternative, emphasizing adjustments to some commonly used interval estimators for population-based rates and rate ratios. The adjusted estimators involve relatively simple closed-form computations, which in the absence of multiple-case incidents reduce to familiar estimators based on the simpler Poisson model. Summary data from the National Violent Death Reporting System are referenced in several examples demonstrating application of the proposed methodology.

    PMID:
    17306020
    [PubMed]
    PMCID: PMC1828152
    Free PMC Article

      Supplemental Content

      Click here to read Click here to read

      Recent activity

      Your browsing activity is empty.

      Activity recording is turned off.

      Turn recording back on

      See more...
      Write to the Help Desk