Related Experiment Videos

Causal inference in infectious diseases

M E Halloran1, C J Struchiner

  • 1Department of Biostatistics, Rollins School of Public Health, Emory University, Atlanta, GA 30322, USA.

Insights

This study reviews Rubin's causal inference model for infectious diseases, highlighting how dependent outcomes (like infections spreading) violate standard assumptions and require new methods to analyze direct and indirect effects.

Area of Science:

  • Epidemiology
  • Causal Inference
  • Biostatistics

Background:

  • Rubin's causal inference model, widely used since the 1970s, assumes independence of outcomes between individuals.
  • Infectious disease dynamics often exhibit 'dependent happenings,' where one person's infection status depends on others.
  • This violates the stability assumption crucial for standard causal inference models.

Purpose of the Study:

  • To review Rubin's causal inference model in the context of infectious diseases.
  • To explore the consequences of violating the stability assumption in infectious disease studies.
  • To define and analyze causal effects, including direct and indirect effects, in the presence of dependent outcomes.

Main Methods:

  • Review of Rubin's potential outcomes framework for causal inference.
  • Adaptation of the model to account for 'dependent happenings' in infectious disease transmission.
  • Formal definition of transmission probability as an average causal parameter.
  • Analysis of challenges in defining unconditional indirect and total effects.

Main Results:

  • Violation of the stability assumption necessitates an expanded outcome representation.
  • Direct and indirect effects, including changes in susceptibility and infectiousness, become key considerations.
  • Defining unconditional indirect and total effects within this framework presents formal challenges.
  • The assignment mechanism's influence on exposure complicates causal effect estimation.

Conclusions:

  • The standard Rubin model requires adaptation for infectious disease causal inference due to dependent outcomes.
  • New approaches are needed to formally define and estimate indirect and total effects in these settings.
  • Differential exposure to infection plays a critical role in understanding direct versus indirect effects.

Related Concept Videos