• Communications for Statistical Applications and Methods
• /
• v.8 no.2
• /
• pp.427-434
• /
• 2001

In this paper, we consider the nonparametric Bayesian approach to the multiple comparisons problem for I Poisson populations using Dirichlet process priors. We describe Gibbs sampling algorithm for calculating posterior probabilities for the hypotheses and calculate posterior probabilities for the hypotheses using Markov chain Monte Carlo. Also we provide a numerical example to illustrate the developed numerical technique.

• Communications for Statistical Applications and Methods
• /
• v.3 no.2
• /
• pp.187-195
• /
• 1996

This paper deals with the stochastic comparisons of order statistics from independent but nonidentically distributed (i.n.i.d) variates. And we consider order statistics under positive dependence, negative dependence, and exchangeability.

• Journal of the Korean Statistical Society
• /
• v.23 no.1
• /
• pp.53-62
• /
• 1994

When a comparison is made with respect to the unknown best treatment, Hsu (1984, 1985) proposed the so called multiple comparisons procedures with the best in the analysis of variance model. Applying Hsu's results to the analysis of covariance model, simultaneous confidence intervals for multiple comparisons with the best in a balanced one-way layout with a random covariate are developed and are applied to a real data example.

• Journal of the Korean Statistical Society
• /
• v.20 no.1
• /
• pp.44-56
• /
• 1991

For all pairwise comparisons of treatments, Bayesian simultaneous confidence intervals are proposed and studied. First Bayesian solutions are obtained for a fixed prior, and then prior parameters are estimated by a parametric empirical Bayesian method. The nominal confidence level is shown to be controlled asymptotically. An extension to the unbalanced design is also considered.

• Communications for Statistical Applications and Methods
• /
• v.9 no.3
• /
• pp.733-741
• /
• 2002

A class of block designs for general combining ability comparisons within two groups of inbred lines in diallel crosses is given. These block designs are constructed by using balanced block designs obtained by cyclically developing a single initial block. Also, the efficiencies of block designs are tabulated for number of lines 26 or less.

• Journal of the Korean Statistical Society
• /
• v.24 no.1
• /
• pp.161-181
• /
• 1995

The goal of this article is to study the performances of various empirical Bayes simultaneous interval estimates for all pairwise comparisons. The considered empirical Bayes interval estimaters are those based on unbiased estimate, a hierarchical Bayes estimate and a constrained hierarchical Bayes estimate. Simulation results for small sample cases are given and an illustrative example is also provided.

• Journal of the Korean Statistical Society
• /
• v.18 no.2
• /
• pp.135-148
• /
• 1989

Cumulative sum schemes based on a weighted score are considered for controlling the mean of a continuous production process; in which both the one-sided and two-sided schemes are proposed. The average run lengths and the run length distributions for the proposed schemes are obtained by the Markov chain approach. Comparisons by the average run length show that the proposed schemes perform nearly as well as the standard cumulative sum schemes in detecting changes in the process mean. Comparisons of the one-sided schemes by the run length distribution are also presented.

• Communications for Statistical Applications and Methods
• /
• v.9 no.2
• /
• pp.443-450
• /
• 2002

In this paper, block designs for control versus test comparisons among the lines for diallel crosses are proposed. These block designs are constructed by using balanced incomplete block designs. Also, the efficiencies of the diallel crosses block designs obtained through this method are tabulated for number of lines 23 or less.

• Communications for Statistical Applications and Methods
• /
• v.5 no.2
• /
• pp.417-429
• /
• 1998

This paper compares powers of the two nonparametric tests under a variety of population distributions through a simulation study. Both tests require that the two underlying populations have the same variance, but this assumption is relaxed in some of the comparisons.

• Proceedings of the Korean Statistical Society Conference
• /
• 2002.05a
• /
• pp.165-170
• /
• 2002

Sometimes we have two groups of inbred lines and there are only interest in gca comparisons within group($p_{1}$) and group($p_{2}$) and not between two groups. For example, suppose there two Lab, each of the 2 Labs have obtained the best lines. For this purpose we now give a method of constructing block designs for diallel cross experiments and we will explain how to calculate efficiency. Then we show the efficiencies in the table.