• The Journal of the Korea institute of electronic communication sciences
• /
• v.5 no.5
• /
• pp.435-443
• /
• 2010

When testing systems that incorporate probabilistic behavior, it is necessary to apply test inputs a number of times in order to give a test verdict. Interval estimation can be used to assert the correctness of probabilities where the selection of confidence interval is one of the important issues for quality of testing. The Wald interval has been widely accepted for interval estimation. In this paper, we compare the Wald interval and the Agresti-Coull interval for various sizes of samples. The comparison is carried out based on the test pass probability of correct implementations and the test fail probability of incorrect implementations when these confidence intervals are used for probability testing. We consider two-sided confidence intervals to check if the probability is close to a given value. Also one-sided confidence intervals are considered in the comparison in order to check if the probability is not less than a given value. When testing probabilities using two-sided confidence intervals, we recommend the Agresti-Coull interval. For one-sided confidence intervals, the Agresti-Coull interval is recommended when the size of samples is large while either one of two confidence intervals can be used for small size samples.

• The Korean Journal of Applied Statistics
• /
• v.25 no.4
• /
• pp.697-706
• /
• 2012

An Agresti-Coull type test is considered for the difference of binomial proportions in two doubly sampled data subject to common false-positive error. The performance of the test is compared with likelihood-based tests. The Agresti-Coull test has many desirable properties in that it can approximate the nominal significance level well, and has comparable power performance with a computational advantage.

• Journal of the Korean Statistical Society
• /
• v.36 no.2
• /
• pp.275-284
• /
• 2007

Confidence intervals for the population proportion in a double sampling scheme subject to false-positive misclassification are considered. The confidence intervals are obtained by applying Agresti and Coull's approach, so-called "adding two-failures and two successes". They are compared in terms of coverage probabilities and expected widths with the Wald interval and the confidence interval given by Boese et al. (2006). The latter one is a test-based confidence interval and is known to have good properties. It is shown that the Agresti and Coull's approach provides a relatively simple but effective confidence interval.

• The Korean Journal of Applied Statistics
• /
• v.25 no.3
• /
• pp.513-520
• /
• 2012

An Agresti-Coull type test is considered for the difference of binomial proportions in two doubly sampled data subject to false-positive error. The performance of the test is compared with the likelihood-based tests. It is shown that the Agresti-Coull test has many desirable properties in that it can approximate the nominal significance level with compatible power performance.