독립표본에서 두 모비율의 차이에 대한 가중 POLYA 사후분포 신뢰구간 = The Weighted Polya Posterior Confidence Interval For the Difference Between Two Independent Proportions

다국어 초록 (Multilingual Abstract)

The Wald confidence interval has been considered as a standard method for the difference of proportions. However, the erratic behavior of the coverage probability of the Wald confidence interval is recognized in various literatures. Various alternatives have been proposed. Among them, Agresti-Caffo confidence interval has gained the reputation because of its simplicity and fairly good performance in terms of coverage probability. It is known however, that the Agresti-Caffo confidence interval is conservative. In this note, a confidence interval is developed using the weighted Polya posterior which was employed to obtain a confidence interval for the binomial proportion in Lee(2005). The resulting confidence interval is simple and effective in various respects such as the closeness of the average coverage probability to the nominal confidence level, the average expected length and the mean absolute error of the coverage probability. Practically it can be used for the interval estimation of the difference of proportions for any sample sizes and parameter values.

참고문헌 (Reference)

1 이승천, "이항 비율의 가중 Polya posterior 구간추정" 한국통계학회 18 (18): 607-615, 2005

2 정형철, "모비율 차이의 신뢰구간들에 대한 비교연구" 한국통계학회 16 (16): 16-393, 2003

3 Newcombe, R, "Two-sided con¯dence intervals for the single proportion: Comparison of seven methods" (17) : 857-872, 1998

4 Chan, I. S. F, "Test-based exact con¯dence intervals for the difference of two binomial proportions" (55) : 1202-1209, 1999

5 Santner, T. J, "Small-sample confidence intervals for p1-p2 and p1/p2 in 2x2 contingency tables" (17) : 873-890, 1980

6 Agresti, A, "Simple and effective con¯dence intervals for proportions and differences of proportions result from adding two successes and two failures" (54) : 280-288, 2000

7 Wilson, E. B, "Probable inference, the law of succession and statistical inference" (22) : 209-212, 1927

8 Anbar, D., "On estimating the di®erence between two probabilities with special reference to clinical trials" (39) : 257-262, 1983

9 Meeden, G. D, "Interval estimators for the population mean for skewed distributions with a small sample size" (26) : 81-96, 1999

10 Newcombe, R, "Interval estimation for the difference between independent proportions: Comparison of eleven methods" (17) : 873-890, 1998

11 Brown, L. D, "Interval estimation for a binomial proportion" (16) : 101-133, 2001

12 Brown, L. D, "Con¯dence intervals for a binomial proportion and asymptotic expansions" (30) : 160-201, 2002

13 Mee, R, "Con¯dence bounds for the difference between two probabilities" (40) : 1175-1176, 1984

14 Vollet, S. E, "Confidence intervals for a binomial proportion" (12) : 809-824, 1993

15 Blyth, C. R, "Binomial con¯dence intervals" (78) : 108-116, 1983

16 Ghosh, M, "Bayesian methods for ¯nite population sampling" Chapman & Hall, London 1998

17 Beal, S. L., "Asymptotic con¯dence intervals for the difference between two binomial parameters for use with small samples" (43) : 941-950, 1987

18 Agresti, A, "Approximation is better than "exact" for interval estimation of binomial proportions" (52) : 119-126, 1998

19 Feller, W, "An introduction of probability theory and its applications vol.1" Wiley, New York 1968

20 Ghosh, B. K, "A comparison of some approximate con¯dence intervals for the binomial parameter" (74) : 894-900, 1979