Talk:Fiducial inference

From Wikipedia, the free encyclopedia
Jump to: navigation, search
WikiProject Statistics (Rated C-class, Mid-importance)
WikiProject icon

This article is within the scope of the WikiProject Statistics, a collaborative effort to improve the coverage of statistics on Wikipedia. If you would like to participate, please visit the project page or join the discussion.

C-Class article C  This article has been rated as C-Class on the quality scale.
 Mid  This article has been rated as Mid-importance on the importance scale.
 

I have written a short introduction to fiducial inference to start the ball rolling. It is not yet highly polished, but it's a start. I would sign my name, but after dozens of attempts to create a username that was accepted by the system, I gave up ("only takes a few seconds"--yeah right!)218.101.112.213 08:04, 3 November 2007 (UTC) On reading the entry, I find it needs a lot more work. I am now working on polishing it (and have now managed to find an acceptable user name).TerryM--re (talk) 21:39, 17 November 2007 (UTC)

Quotations should have quotation marks[edit]

The phrase "not a probability distribution in the usual sense" appears on page 156 of Stuart, Ord, and Arnold, which tries to update Kendall and Stuart. (I removed the "neither truthful nor 'good faith' in the usual sense" phrase.) Kiefer.Wolfowitz (talk) 20:59, 11 March 2010 (UTC)

"Obsolete" scientific theories[edit]

In the categories "obsolete statistical theories" or "obsolete statitistical procedures", the adjective "obsolete" was chosen for compatibility with the super-category "obsolete scientific theories". Would Melcombe and other editors suggest an appropriate term to replace "obsolete" --- e.g., would "widely deprecated" be acceptable? 20:24, 12 March 2010 (UTC)

Resurrection[edit]

I added the quote from Davison, in Cox's collection from Biometrika. Even the most renowned statisticians associated with the neo-Fisherian revival of the 1970s clasify efforts at resurrecting "fiducial inference" as a form of necromancy, if I may state my POV here. Kiefer.Wolfowitz (talk) 22:13, 12 March 2010 (UTC)

Original research tags[edit]

Melcombe's stating that a remake of Kendall's dictionary mumbles something about fiducial inference (under statistical inference) was original research. My stating that a better dictionary (also based on Kendall's) doesn't mention fiducial inference under statistical inference is also original research. Both statements should be deleted.

It is inappropriate that Kendall is being used as the main source for this article, since Kendall's reliability has waned, while the reliability of Cox and his students (Hinkley and Davison) have waxed, and they don't repeat Kendall's weird tics about the confusion between confidence intervals and "fiducial intervals". (Kendall's statements of the 1940s would have been appropriate sources for a 1940s Wikipedia.) Thanks, Kiefer.Wolfowitz (talk) 21:51, 23 March 2010 (UTC)