Talk:Interval estimation

Relevance
Can anyone say why


 * Behrens-Fisher problem
 * fiducial inference

might be relevant and indicate relevance in article if appropriate.Melcombe (talk) 17:35, 27 February 2008 (UTC)


 * The Behrens-Fisher problem is often regarded as the problem of finding an interval estimate of the difference between the expected values of two normally distributed populations. Of course one could do hypothesis testing for the difference between the two means and plausibly say that that's also about the Behrens-Fisher problem, so the B-F problem is not ONLY about interval estimation.  And fiducial inference is usually about fiducial intervals. Michael Hardy (talk) 22:13, 27 February 2008 (UTC)


 * OK I have made some reaarangements to reflect this. Regarding the B-F problem, I was wondering about the relevance of mentioning it at all in the article, but I have now put in something that tries to make it seem relevant. Does this reflecrt why it was put here? Melcombe (talk) 10:29, 28 February 2008 (UTC)