Approximate is Better than “Exact” for Interval Estimation of Binomial Proportions

Abstract For interval estimation of a proportion, coverage probabilities tend to be too large for “exact” confidence intervals based on inverting the binomial test and too small for the interval based on inverting the Wald large-sample normal test (i.e., sample proportion ± z-score × estimated standard error). Wilson's suggestion of inverting the related score test with null rather than estimated standard error yields coverage probabilities close to nominal confidence levels, even for very small sample sizes. The 95% score interval has similar behavior as the adjusted Wald interval obtained after adding two “successes” and two “failures” to the sample. In elementary courses, with the score and adjusted Wald methods it is unnecessary to provide students with awkward sample size guidelines.

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

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

[3]  J. Neyman,et al.  On the Problem of Confidence Intervals , 1935 .

[4]  F. Garwood,et al.  i) Fiducial Limits for the Poisson Distribution , 1936 .

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

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

[7]  S. Maclane,et al.  Edwin Bidwell Wilson. , 1973, Biographical memoirs. National Academy of Sciences.

[8]  W. Meredith,et al.  Statistics and Data Analysis , 1974 .

[9]  B. K. Ghosh,et al.  A Comparison of Some Approximate Confidence Intervals for the Binomial Parameter , 1979 .

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

[11]  D. Duffy,et al.  Confidence Intervals for a Binomial Parameter Based on Multistage Tests , 1987 .

[12]  D. G. Simpson,et al.  The Statistical Analysis of Discrete Data , 1989 .

[13]  Hanfeng Chen The Accuracy of Approximate Intervals for a Binomial Parameter , 1990 .

[14]  A. Agresti An introduction to categorical data analysis , 1997 .

[15]  Cyrus R. Mehta,et al.  Comparison of Exact, Mid-p, and Mantel–Haenszel Confidence Intervals for the Common Odds Ratio Across Several 2 × 2 Contingency Tables , 1992 .

[16]  Kishor S. Trivedi,et al.  A COMPARISON OF APPROXIMATE INTERVAL ESTIMATORS FOR THE BERNOULLI PARAMETER , 1993 .

[17]  S E Vollset,et al.  Confidence intervals for a binomial proportion. , 1994, Statistics in medicine.

[18]  Better approximate confidence intervals for a binomial parameter , 1994 .

[19]  M. Edwardes,et al.  Confidence intervals for a binomial proportion by S. E. Vollset, Statistics in Medicine, 12, 809-824 (1993) , 1994, Statistics in medicine.

[20]  A note on the accuracy of an approximate interval for the binomial parameter , 1995 .

[21]  P. Laplace Théorie analytique des probabilités , 1995 .

[22]  A Note on Teaching Binomial Confidence Intervals , 1997 .

[23]  Bradley P. Carlin,et al.  BAYES AND EMPIRICAL BAYES METHODS FOR DATA ANALYSIS , 1996, Stat. Comput..

[24]  B. Jovanovic,et al.  A Look at the Rule of Three , 1997 .

[25]  Karen A. F. Copeland An Introduction to Categorical Data Analysis , 1997 .

[26]  Thomas J. Santner,et al.  Teaching Large‐Sample Binomial Confidence Intervals , 1998 .