Abstract
Gastwirth, Krieger, and Rosenbaum used statistical evidence from a 1987 sex discrimination case in a Canadian court as the basis for a November 1994 article in The American Statistician on the “third variable” problem in correlational analysis. We reexamine their unsettling conclusion that the Court “accepted an impossible explanation.” A revised explanatory model that includes an unmeasured latent variable leads us to a very different conclusion. The result demonstrates that references to unmeasured covariates as “third variables” in analyses of spurious association can be quite difficult or even impossible to evaluate statistically. Judging such models may depend ultimately on assessing their plausibility rather than their statistical possibility.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
