Ambient particulate matter and health effects: publication bias in studies of short-term associations

Epidemiology. 2005 Mar;16(2):155-63. doi: 10.1097/01.ede.0000152528.22746.0f.


Background: Time-series studies have shown short-term temporal associations between low levels of ambient particulate air pollution and adverse health effects. It is not known whether or to what extent this literature is affected by publication bias.

Methods: We obtained effect estimates from time-series studies published up to January 2002. These were summarized and examined for funnel plot asymmetry. We compared summary estimates between single-city and prospective multicity studies. Using 1 multicity study, we examined the sensitivity of summary estimates to alternative lag selection policies.

Results: We found evidence for publication bias among single-city studies of daily mortality, hospital admissions for chronic obstructive lung disease (COPD), and incidence of cough symptom, but not for studies of lung function. Statistical correction for this bias reduced summary relative risk estimates for a 10 microg/m increment of particulate matter less than 10 microm aerodynamic diameter (PM10) as follows: daily mortality from 1.006 to 1.005 and admissions for COPD from 1.013 to 1.011; and odds ratio for cough from 1.025 to 1.015. Analysis of results from a large multicity study suggested that selection of positive estimates from a range of lags could increase summary estimates for PM10 and daily mortality by up to 130% above those based on nondirectional approaches.

Conclusion: We conclude that publication bias is present in single-city time-series studies of ambient particles. However, after correcting for publication bias statistically, associations between particles and adverse health effects remained positive and precisely estimated. Differential selection of positive lags may also inflate estimates.

Publication types

  • Evaluation Study
  • Research Support, Non-U.S. Gov't

MeSH terms

  • Air Pollutants / poisoning*
  • Cities
  • Environmental Health*
  • Humans
  • Mortality / trends
  • Particle Size
  • Prospective Studies
  • Publication Bias*
  • Time Factors


  • Air Pollutants