Causal Inference

  • David Edwards
Part of the Springer Texts in Statistics book series (STS)


The study of cause and effect relationships is central to much empirical research: consider, for example, studies to identify the causal risk-factors for a disease, or studies that attempt to predict the effect of policy changes. Graphical models may be very useful in such endeavours, by helping to reveal the associational structure of the data. In so doing they may often, as Cox and Wermuth (1996) put it, “point towards explanations that are potentially causal.” Since the graphs, particularly the directed graphs, resemble causal networks, it is natural to interpret them in causal terms; perhaps this even happens unconsciously. The key question is therefore: When are such causal interpretations justified? Or in other words, is it ever legitimate to claim that an analysis provides evidence of a causal connection? In this chapter we attempt to clarify this and related issues.


Propensity Score Causal Effect Causal Inference Causal Model Treatment Allocation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer Science+Business Media New York 2000

Authors and Affiliations

  • David Edwards
    • 1
  1. 1.Statistics DepartmentNovo Nordisk A/SBagsvaerdDenmark

Personalised recommendations