Interval estimation for the difference between independent proportions: comparison of eleven methods
Statistics in MedicinePublished 30 April 1998
Robert G. Newcombe
Citations1,806
SJR quartileQ1
SJR score1.27
SNIP1.33
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
Two new approaches which also avoid aberrations are developed and evaluated, and a tail area profile likelihood based method produces the best coverage properties, but is difficult to calculate for large denominators.
Abstract
Several existing unconditional methods for setting confidence intervals for the difference between binomial proportions are evaluated. Computationally simpler methods are prone to a variety of aberrations and poor coverage properties. The closely interrelated methods of Mee and Miettinen and Nurminen perform well but require a computer program. Two new approaches which also avoid aberrations are developed and evaluated. A tail area profile likelihood based method produces the best coverage properties, but is difficult to calculate for large denominators. A method combining Wilson score intervals for the two proportions to be compared also performs well, and is readily implemented irrespective of sample size.
Keywords
MathematicsDecision Sciences
Wiley series in probability and statisticsStatistical Methods for Rates and Proportions
18,048 Citations2003Joseph L. Fleiss, Bruce Levin +1 more
Statistical Methods in Cancer Research
6,727 Citations1980N. E. Breslow
Statistics in MedicineTwo-sided confidence intervals for the single proportion: comparison of seven methods
5,075 Citations1998Robert G. Newcombe
Criteria appropriate to the evaluation of various proposed methods for interval estimate methods for proportions include: closeness of the achieved coverage probability to its nominal value; whether intervals are located too close to or too distant from the middle of the scale; expected interval width; avoidance of aberrations such as limits outside [0,1] or zero width intervals; and ease of use.
BiometrikaTHE USE OF CONFIDENCE OR FIDUCIAL LIMITS ILLUSTRATED IN THE CASE OF THE BINOMIAL
4,753 Citations1934C. J. Clopper, E. S. Pearson
Journal of the American Statistical AssociationProbable Inference, the Law of Succession, and Statistical Inference
3,502 Citations1927Edwin B. Wilson
Journal of the Royal Statistical Society Series B (Statistical Methodology)Parameter Orthogonality and Approximate Conditional Inference
1,392 Citations1987D. R. Cox, Nancy Reid
Statistics in MedicineComparative analysis of two rates
1,107 Citations1985Olli S. Miettinen, Markku Nurminen
This paper examines comparative analysis of rates with a view to each of the usual comparative parameters-rate difference, rate ratio and odds ratio with particular reference to first principles, and stresses the need for restricted estimation of variance in the chi-square function underlying interval estimation.
Statistics in MedicineConfidence intervals for a binomial proportion
485 Citations1993Stein Emil Vollset
Thirteen methods for computing binomial confidence intervals are compared based on their coverage properties, widths and errors relative to exact limits, and the continuity corrected score method is recommended over exact methods.
Journal of the American Statistical AssociationBinomial Confidence Intervals
408 Citations1983Colin R. Blyth, Harold A. Still
JNCI Journal of the National Cancer InstituteBreast Cancer in Women After Repeated Fluoroscopic Examinations of the Chest2
249 Citations1977John D. Boice, Richard R. Monson
BiometrikaTHE COMBINATION OF PROBABILITIES ARISING FROM DATA IN DISCRETE DISTRIBUTIONS
189 Citations1949H. O. Lancaster
American Journal of Public Health and the Nations HealthThe Relationship of Reported Coronary Heart Disease Mortality to Physical Activity of Work
147 Citations1963Harold A. Kahn
Journal of the Royal Statistical Society Series D (The Statistician)Mid-P Confidence Intervals: A Brief Review
141 Citations1995Geoffrey Berry, P. Armitage
BMJShort term treatment of dermatophyte onychomycosis with terbinafine.
132 Citations1992Mark Goodfield, L. Andrew +1 more
12 weeks' terbinafine is effective and safe treatment for nail dermatophytosis.
British Journal of DermatologySmoking habits in psoriasis: a case control study
129 Citations1992Caroline Mills, E D Srivastava +5 more
Examination of smoking habits in 108 patients with psoriasis, including some with palmoplantar distribution, and compared the results with matched controls from the community found smoking may play a role in the aetiology of this common skin disorder.
BiometricsAsymptotic Confidence Intervals for the Difference between Two Binomial Parameters for Use with Small Samples
86 Citations1987Stuart L. Beal
Five asymptotically-based confidence intervals for the difference between the binomial parameters from two binomial populations are described, including the usual simple interval, which is extensively evaluated in terms of actual confidence level and interval length.
BiometricsApproximate Interval Estimation of the Difference in Binomial Parameters: Correction for Skewness and Extension to Multiple Tables
69 Citations1990John J. Gart, Jun‐mo Nam
Good approximate interval estimates for differences, ratios, and odds ratios of binomial parameters can all be derived from the same general theory.
BiometricsOn Estimating the Difference between Two Probabilities, with Special Reference to Clinical Trials
38 Citations1983Dan Anbar
The problem of estimating the difference between the probabilities of 'success' for two binomial experiments is considered and confidence intervals based on large-sample theory are constructed and some of their properties are compared with those of a simple technique based on exact distributions.
Statistics in MedicineA NON-ITERATIVE ACCURATE ASYMPTOTIC CONFIDENCE INTERVAL FOR THE DIFFERENCE BETWEEN TWO PROPORTIONS
30 Citations1997Sylvan Wallenstein
A new confidence interval for the difference between two binomial probabilities that requires only the solution of a quadratic equation is proposed, which appears to yields actual 95 per cent confidence intervals with mean or median probabilities of coverage very close to 0.95.