The individualistic fallacy, ecological studies and instrumental variables: A causal interpretation

Tom Loney, Nico J. Nagelkerke

Research output: Contribution to journalReview articlepeer-review

46 Citations (Scopus)

Abstract

The validity of ecological studies in epidemiology for inferring causal relationships has been widely challenged as observed associations could be biased by the Ecological Fallacy. We reconsider the important design components of ecological studies, and discuss the conditions that may lead to spurious associations. Ecological associations are useful and valid when the ecological exposures can be interpreted as Instrumental Variables. A suitable example may be a time series analysis of environmental pollution (e.g. particulate matter with an aerodynamic diameter of <10 micrometres; PM10) and health outcomes (e.g. hospital admissions for acute myocardial infarction) as environmental pollution levels are a cause of individual exposure levels and not just an aggregate measurement. Ecological exposures may also be employed in situations (perhaps rare) where individual exposures are known but their associations with health outcomes are confounded by unknown or unquantifiable factors. Ecological associations have a notorious reputation in epidemiology and individualistic associations are considered superior to ecological associations because of the "ecological fallacy". We have argued that this is incorrect in situations in which ecological or aggregate exposures can serve as an instrumental variable and associations between individual exposure and outcome are likely to be confounded by unmeasured variables.

Original languageEnglish
Article number18
JournalEmerging Themes in Epidemiology
Volume11
Issue number1
DOIs
Publication statusPublished - Nov 2014
Externally publishedYes

Keywords

  • Aggregate studies
  • Bias
  • Ecological fallacy
  • Environmental health
  • Instrumental variables
  • Methodological individualism

ASJC Scopus subject areas

  • Epidemiology

Fingerprint

Dive into the research topics of 'The individualistic fallacy, ecological studies and instrumental variables: A causal interpretation'. Together they form a unique fingerprint.

Cite this