A FAMILY OF SIMULTANEOUS CONFIDENCE INTERVALS FOR MULTINOMIAL PROPORTIONS
Resource
COMPUTATIONAL STATISTICS & DATA ANALYSIS v.43 n.1 pp.29-45
Journal
COMPUTATIONAL STATISTICS & DATA ANALYSIS
Journal Volume
v.43
Journal Issue
n.1
Pages
29-45
Date Issued
2003
Date
2003
Author(s)
TAI, JOHN, JEN
Abstract
A family of simultaneous confidence intervals (SCIs) for multinomial proportions is proposed by inverting the power- divergence statistics and the best SCIs in the family is determined, by Monte-Carlo technique. Numerical comparisons of this method with the other alternatives are presented. Simulation results indicate that the new procedure is preferable to all its competitors in most cases.
Subjects
coverage probability
Monte-Carlo method
power-divergence statistic
simultaneous confidence intervals
sparse data
Type
journal article