Bootstrap Method for Categorical Data Analysis: revisited

Myoungshic Jhun, AMS SUNY Korea

Starting with the asymptotic properties for lattice case, the bootstrap method is used for the construction of simultaneous confidence regions for proportions of single and several multinomial populations. Furthermore, the bootstrap method is also applied to the test for independence in two-way ordinal contingency tables. Proposed bootstrap method is compared with the other methods in terms of average coverage probability by Monte Carlo simulation. Advantages of the proposed method are discussed.