The Behrens-Fisher and Fieller-Creasy Problems
Of all R.A. Fisher’s creations, fiducial inference was perhaps the most ambitious, yet least accepted. Ignored by a large part of the statistics community satisfied with the mathematically simpler confidence approach, and rejected as logically imperfect and inconsistent in general by those who recognized the strength of the fiducial objectives, the fiducial argument continues under active and sympathetic study today only in a few islands of the statistical world.
KeywordsReference Distribution Population Fraction Pivotal Quantity Fiducial Probability Confidence Approach
Unable to display preview. Download preview PDF.
- Behrens, W.V. (1929). “Ein Betrag zur Fehlerberechnung bei weniger Beobachtungen,” Landwirtschaftliche Jahrbücher, 68, 807–837.Google Scholar
- Box, Joan Fisher (1978). R.A. Fisher: The Life of a Scientist. New York: John Wiley and Sons.Google Scholar
- Irwin, J.O., et al. (1954). “Discussion on the Symposium on Interval Estimation,” Journal of the Royal Statistical Society, Series B, 16, 204–222.Google Scholar
- Johnson, Palmer O. and J. Neyman (1936). “Tests of Certain Linear Hypotheses and Their Application to Some Educational Problems,” Statistical Research Memoirs, 1, 57–93.Google Scholar
- Smith, H.F. (1936). “The Problem of Comparing the Results of Two Experiments with Unequal Errors,” Council of Scientific and Industrial Research (Australia), Journal, 9, 211–212.Google Scholar
- Snedecor, G.W. (1946). Statistical Methods, 4th Edition. Ames: Iowa State College Press.Google Scholar
- Welch, B.L. (1937). “The Significance of the Difference Between Two Means when the Population Variances are Unequal,” Biometrika, 29, 350–362.Google Scholar