« Judicature and Scientific Evidence | Main | Global Warming Study Group? »

December 5, 2006

The Supreme Court and Science

Nice article here about the intersection of law and science, and particularly at the Supreme Court.  See Here.

December 5, 2006 | Permalink

TrackBack

TrackBack URL for this entry:
http://www.typepad.com/services/trackback/6a00d8341bfae553ef00d8345f3f2869e2

Listed below are links to weblogs that reference The Supreme Court and Science:

» Expert Law: Sources and Resources. from Insurance Claims and Bad Faith Law Blog
An outstanding new newspaper Commentary analyzes the development of Expert Opinion Evidence in the Courts from Frye (1923) to Daubert (1993) to today in When Questions of Science Come to a Courtroom, Truth Has Many Faces, by Cornelia Dean and [Read More]

Tracked on Dec 7, 2006 5:21:56 AM

Comments

David is being modest here. Readers of the N.Y. Times commentary will find him quoted there. They also will find the following, much less sensible observation:

Typically, scientists don’t accept a finding unless, statistically, the odds are less than 1 in 20 that it occurred by chance. This standard is higher than the typical standard of proof in civil trials (“preponderance of the evidence”) and lower than the standard for criminal trials (“beyond a reasonable doubt”).

The legal standard pertains to the probability of a hypothesis given the data. The scientific standard applies to the probability of the data given the null hypothesis. "Statistical significance" does not mean that the null hypothesis has a 1/20 chance (or less) of being true. See, e.g., D.H. Kaye, Statistical Significance and the Burden of Persuasion, Journal of Law and Contemporary Problems, Vol. 46, No. 4, Autumn 1983, pp. 13-23.

Statisticians call this mistake in the Times article the "transposition fallacy." It crops up all the time in opinions involving statistical proof.

--DHK

Posted by: DH Kaye | Dec 5, 2006 9:05:54 PM

Post a comment