WbinoCI: An Admissible Exact Confidence Interval for the Bnomial Proportion
Description
An admissible exact confidence interval of level 1-alpha is
constructed for the binomial proportion p. This function can be used to
calculate the interval constructed method proposed by Wang (2014).
Usage
WbinoCI(x, n, conf.level = 0.95, details = FALSE)
Value
A list which contains the confidence interval (CI) of the sample
point and the confidence intervals (CIM) for all the points and the icp.
Arguments
x
the number of success or the observed data.
n
the sample size.
conf.level
Confidence level. The default is 0.95.
details
TRUE/FALSE, can be abbreviated. To choose whether to compute
the confidence interval for the whole sample points and output the infimum
coverage probability. The default is FALSE.
Details
Suppose X~bino(n,p), the sample space of X is {0,1,...,n}. Wang
(2014) proposed an admissible interval which is obtained by uniformly
shrinking the initial 1-alpha Clopper-Pearson interval from the middle to
both sides of the sample space iteratively. This interval is admissible so
that any proper sub-interval of it cannot assure the confidence coefficient.
This means the interval cannot be shortened anymore.
References
Clopper, C. J. and Pearson, E. S. (1934). The use of confidence
or fiducial limits in the case of the binomial. "Biometrika" 26: 404-413.
Wang, W. (2014). An iterative construction of confidence
intervals for a proportion. "Statistica Sinica" 24: 1389-1410.