二项分布的区间估量分析.pdfVIP

  Æ Æ  Wald Wilson Bayes A-C CIAC = p˜ ± κ(˜pq˜)1/2n˜−1/2 Wilson κn1/2 κ2 CIW = p˜ ± n + κ2 (ˆpqˆ+ 4n )1/2 Æ ℄ i     Wilson AC Jeffreys ℄  Æ   : Æ ii ABSTRACT Interval estimation is a important part in mathematical statistics.In this dis- sertation, we investigate the interval estimation for the parameter in binomial distri- bution,which is a basic problem.On account of the importance of this subject,there has a uniform expression among textbooks.There also has further research and in- troduction and some confidence intervals accepted by people have been given among literatures. However,via intensive numerical computation,the author finds that actually some characteristics of this confidence intervals,such as,coverage probability,coverage efficiency and expected length etc fluctuate intensely when the sample size varies given the parameter,or when the parameter varies given the sample size because of the discreteness of binomial distribution.