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

Exploring bias in a generalized additive model for spatial air pollution data.

Timothy Ramsay1, Richard Burnett, Daniel Krewski

  • 1R. Samuel McLaughlin Centre for Population Health Risk Assessment, Ottawa, Ontario, Canada. tramsay@uottawa.ca

Environmental Health Perspectives
|August 5, 2003
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

Practices and perceptions of advanced endoscopic imaging techniques for colorectal neoplasia detection in patients with inflammatory bowel disease: report of a survey among Canadian inflammatory bowel disease specialists.

iGIE : innovation, investigation and insights·2026
Same author

Meteorologically Driven Changes in Future Global Air Quality: Physical and Monetized Impacts.

Environmental science & technology·2026
Same author

Effect of PCC on Thrombin Generation in Patients on FXaI with Bleeding or Needing Urgent Surgery (GAUGE).

Blood advances·2026
Same author

Antipsychotic Drugs and the Risk of Diabetic Complications: A Systematic Review of Observational Studies.

Journal of clinical medicine·2026
Same author

Understanding how adverse childhood experiences influence the development of postpartum post-traumatic stress disorder: a qualitative study in China.

European journal of psychotraumatology·2026
Same author

Antipsychotic Drugs and the Risk of Diabetic Complications: A Systematic Review of Clinical Evidence.

Journal of clinical medicine·2026
Same journal

A New Start.

Environmental health perspectives·2026
Same journal

Time-Varying Exposure to Element Mixtures and Children's Cognition at 5 Years of Age: Findings from the New Hampshire Birth Cohort Study.

Environmental health perspectives·2026
Same journal

Effect of Household Air Pollution on the Gut Microbiome and Virome of Adult Women Living in Uganda.

Environmental health perspectives·2026
Same journal

Comparison of Temperature-Mortality Associations across the Middle East Using Different Exposure Estimation Approaches.

Environmental health perspectives·2026
Same journal

Workflow for Statistical Analysis of Environmental Mixtures.

Environmental health perspectives·2026
Same journal

Effects of Extreme Heat Exposure on Heatstroke and Liver Injury in Mice: The Role of PPARα.

Environmental health perspectives·2026
See all related articles

Generalized additive models (GAMs) can underestimate standard errors for air pollution effects in spatial epidemiology. Concurvity in spatial data biases risk estimates, necessitating caution when applying GAMs to this data type.

Area of Science:

  • Epidemiology
  • Environmental Health
  • Statistical Modeling

Background:

  • Generalized additive models (GAMs) are widely used in epidemiologic analysis, particularly for assessing air pollution's impact on population health.
  • Recent applications extend GAMs from time-series to spatial data analysis.
  • Concerns exist regarding upward bias in air pollution risk estimates and downward bias in standard errors due to concurvity in time-series data.

Purpose of the Study:

  • To investigate the impact of concurvity in spatial data on air pollution effect estimates within GAMs.
  • To determine if concurvity leads to biased standard error estimates in spatial epidemiologic analyses.
  • To evaluate the influence of concurvity's nature on the bias of air pollution effect estimates.

Main Methods:

Related Experiment Videos

  • Analysis of spatial epidemiologic data using generalized additive models (GAMs).
  • Assessment of concurvity within spatial GAMs.
  • Evaluation of standard error estimation under concurvity conditions.
  • Examination of bias in air pollution effect estimates related to concurvity.

    • Main Results:

    • Concurvity in spatial data can lead to underestimation of standard errors for air pollution effects, even with asymptotically unbiased estimators.
    • The magnitude and direction of bias in air pollution effect estimates are influenced by the characteristics of the concurvity.
    • Including nonparametric functions of location in spatial GAMs is likely to introduce concurvity.

    Conclusions:

    • Caution is advised when utilizing GAMs for spatial epidemiologic data analysis due to potential concurvity.
    • Concurvity poses a risk of biased standard error and effect estimates in spatial air pollution studies.
    • Further research may be needed to develop robust methods for handling concurvity in spatial GAMs.