论文信息 - Were Clopper & Pearson (1934) too careful?

Were Clopper & Pearson (1934) too careful?

The ‘exact’ interval due to Clopper & Pearson (1934) is often considered to be the gold standard for estimating the binomial parameter. However, for practical purposes it is also often considered to be too conservative, when mean rather than minimum coverage close to nominal could be more appropriate. It is argued that (1) Clopper & Pearson themselves changed between these two criteria, (2) ‘approximate’ intervals are preferable to ‘exact’ intervals, and (3) approximate intervals are well represented by Bayesian intervals based on a uniform prior.

Frank Tuyl

[1] K. Mengersen,et al. A Comparison of Bayes–Laplace, Jeffreys, and Other Priors , 2008 .

[2] H. O. Lancaster,et al. Significance Tests in Discrete Distributions , 1961 .

[3] George Casella,et al. Refining binomial confidence intervals , 1986 .

[4] A. Agresti,et al. Approximate is Better than “Exact” for Interval Estimation of Binomial Proportions , 1998 .

[5] E. S. Pearson,et al. THE USE OF CONFIDENCE OR FIDUCIAL LIMITS ILLUSTRATED IN THE CASE OF THE BINOMIAL , 1934 .

[6] J. Kurian,et al. The rule of three , 2001, Anaesthesia.

[7] W. Stevens,et al. Fiducial limits of the parameter of a discontinuous distribution. , 1950, Biometrika.

[8] The Rule of Three, its Variants and Extensions , 2009 .

[9] Edwin L. Crow,et al. CONFIDENCE INTERVALS FOR A PROPORTION , 1956 .

[10] C. Blyth,et al. Binomial Confidence Intervals , 1983 .

[11] Helge Blaker,et al. Confidence curves and improved exact confidence intervals for discrete distributions , 2000 .

[12] E. B. Wilson. Probable Inference, the Law of Succession, and Statistical Inference , 1927 .

[13] L. Brown,et al. Interval Estimation for a Binomial Proportion , 2001 .

[14] H O LANCASTER. The combination of probabilities arising from data in discrete distributions. , 1949, Biometrika.