• Communications for Statistical Applications and Methods
• /
• 제16권2호
• /
• pp.363-372
• /
• 2009

The difference of two independent binomial proportions is frequently of interest in biomedical research. The interval estimation may be an important tool for the inferential problem. Many confidence intervals have been proposed. They can be classified into the class of exact confidence intervals or the class of approximate confidence intervals. Ore may prefer exact confidence interval s in that they guarantee the minimum coverage probability greater than the nominal confidence level. However, someone, for example Agresti and Coull (1998) claims that "approximation is better than exact." It seems that when sample size is large, the approximate interval is more preferable to the exact interval. However, the choice is not clear when sample, size is small. In this note, an exact confidence and an approximate confidence interval, which were recommended by Santner et al. (2007) and Lee (2006b), respectively, are compared in terms of the coverage probability and the expected length.

• Communications for Statistical Applications and Methods
• /
• 제17권3호
• /
• pp.309-318
• /
• 2010

The construction of asymptotic confidence intervals is considered for the difference of binomial proportions in two doubly sampled data subject to false-positive error. The coverage behaviors of several likelihood based confidence intervals and a Bayesian confidence interval are examined. It is shown that a hierarchical Bayesian approach gives a confidence interval with good frequentist properties. Confidence interval based on the Rao score is also shown to have good performance in terms of coverage probability. However, the Wald confidence interval covers true value less often than nominal level.

• Journal of the Korean Data and Information Science Society
• /
• 제13권2호
• /
• pp.355-363
• /
• 2002

Using the Buckley-James method, we construct bootstrap confidence intervals for the regression coefficients under the censored data. And we compare these confidence intervals in terms of the coverage probabilities and the expected confidence interval lengths through Monte Carlo simulation.

• Communications for Statistical Applications and Methods
• /
• 제12권1호
• /
• pp.87-100
• /
• 2005

In order to construct confidence intervals on the sum of variance components in a simple regression model with unbalanced nested error structure, alternative confidence intervals using Graybill and Wang(1980) and generalized inference concept introduced by Tsui and Weerahandi(1989) are proposed. Computer simulation programmed by SAS/IML is performed to compare the simulated confidence coefficients and average interval lengths of the proposed confidence intervals. A numerical example is provided to demonstrate the confidence intervals and to show consistency between the example and simulation results.

• Journal of the Korean Data and Information Science Society
• /
• 제8권2호
• /
• pp.261-270
• /
• 1997

This paper is proposed the parametric empirical Bayes(EB) confidence intervals which corrects the deficiencies in the naive EB confidence intervals of the scale parameter in the Weibull distribution under item-censoring scheme. In this case, the bootstrap EB confidence intervals are obtained by the parametric bootstrap introduced by Laird and Louis(1987). The comparisons among the bootstrap and the naive EB confidence intervals through Monte Carlo study are also presented.

• Communications for Statistical Applications and Methods
• /
• 제10권3호
• /
• pp.997-1005
• /
• 2003

We can use the logistic model for categorical data when the response variables are binary data. In this paper we consider the problem of constructing the confidence intervals for logistic model in I${\times}$J${\times}$2 contingency table. These constructions are simplified by applying logit transformation. This transforms the problem to consider linear form which called the logit model. After obtaining the confidence intervals for the logit model, the reverse transform is applied to obtain the confidence intervals for the logistic model.

• Journal of the Korean Data and Information Science Society
• /
• 제17권3호
• /
• pp.963-972
• /
• 2006

This paper focuses on the likelihood based confidence intervals for two inverse gaussian distributions when the parameter of interest is common scale parameter. Confidence intervals based on signed loglikelihood ratio statistic and modified signed loglikelihood ratio statistics will be compared in small sample through an illustrative simulation study.

• 품질경영학회지
• /
• 제25권1호
• /
• pp.193-203
• /
• 1997

In this paper, we obtain some a, pp.oximate confidence intervals for the reliability of the stress-strength model when the stress and strength each depend on some explanatory variables, respectively. Also we compare the confidence intervals via Monte Carlo simulation.

• 한국전자통신학회논문지
• /
• 제5권5호
• /
• pp.435-443
• /
• 2010

확률적 특성을 가지는 시스템의 시험을 위해서는 시험 입력을 일정 횟수만큼 반복하여 제공하고 관찰된 데이터를 기반으로 판정이 내려져야 한다. 구간 추정 기법을 이용하여 관찰된 데이터로부터 확률 값이 올바른지 여부를 판단할 수 있으며, 이 때 적절한 신뢰구간의 선택은 시험의 품질을 결정하는 중요한 요인이 된다. 본 논문에서는 다양한 크기의 표본에 대해 대표적인 구간 추정 기법인 Wald 신뢰구간과 Agresti-Coull 신뢰구간을 비교 분석한다. 각 신뢰구간이 확률 값 시험에 사용되었을 경우 올바른 구현 제품이 시험을 통과할 확률과 잘못된 구현제품이 시험을 통과하지 못할 확률을 기반으로 비교 분석을 수행하며, 확률 값이 올바른지를 판단하기 위한 양측검정뿐만 아니라 확률 값이 기준 확률 이상인지 여부를 판단하기 위한 단측검정을 사용하는 경우에 대해서도 비교 분석을 수행한다. 비교 분석 결과 양측검정의 경우 Agresti-Coull 신뢰구간을 사용할 것을 추천하며, 단측검정의 경우 큰 크기의 표본에 대해서는 Agresti-Coull 신뢰구간을, 적은 크기의 표본에 대해서는 Wald 신뢰구간 또는 Agresti-Coull 신뢰구간을 선택적으로 사용할 것을 추천한다.

• International Journal of Reliability and Applications
• /
• 제7권2호
• /
• pp.177-186
• /
• 2006

Typical confidence intervals for a mean or mean residual life (MRL) are centered about the mean or mean residual life. We discuss novel confidence intervals that produce statements like "we are 95% confident that the MRL function, e(t), is greater than a prespecified $\mu_o$ for all t in the interval [0, $\hat{\theta})$)" where $\hat{\theta}$ is determined from the sample data, confidence level, and $\mu_o$. Also, we can have statements like 'we are 95% confident that the MRL of population 1, namely $e_1$(t), is greater than the MRL of population 2, $e_2$(t), for all t in the interval [0, $\hat{\theta}$)" where $\hat{\theta}$ is determined from the sample data and confidence level. We illustrate these one and two sample confidence intervals on internal bonds (tensile strengths) for an important modem engineered wood product, called medium density fiberboard (MDF), used internationally.