Understanding Mendelian Randomization
The Wright Stuff: Genes in the Interrogation of Correlation and Causation - George Davey Smith
Eur. J. Pers. 26: 391--413 (2012) DOI: 10.l 002/per
Abstract: The contemporary use of what are now called causal diagrams can be traced back to Sewall Wright's introduction of path coefficients in the early 1920s. Wright was explicit that causal evidence was required to formulate such diagrams and that these schema could not alone provide evidence for or against causality. In population sciences, germline genetic variation can provide required anchors for the separation of causal from (mere) correlational associations. Advances in biological and other material sciences offer more for improved causal understanding than new ways of conceptualising and representing associations. Copyright © 2012 John Wiley & Sons, Ltd.