• Communications for Statistical Applications and Methods
• /
• v.18 no.2
• /
• pp.189-199
• /
• 2011

In this paper, we develop the noninformative priors for the common intraclass correlation coefficient when independent samples drawn from multivariate normal populations. We derive the first and second order matching priors. We reveal that the second order matching prior dose not match alternative coverage probabilities up to the second order and is not a HPD matching prior. It turns out that among all of the reference priors, one-at-a-time reference prior satisfies a second order matching criterion. Our simulation study indicates that one-at-a-time reference prior performs better than the other reference priors in terms of matching the target coverage probabilities in a frequentist sense.

• Journal of the Korean Statistical Society
• /
• v.20 no.2
• /
• pp.191-201
• /
• 1991

Given a set of data pxN$_{i}$, matrices X$_{i}$ observed from p-variate normal populations $\prod$$_{i}$~N($\mu$$_{I}$, $\Sigma$$_{i}$) for i=1, …, K, the test for equality form of the covariance matrices is to choose a hypothetical model which best explains the homogeneity/heterogeneity structure across the covariance matrices among the hypothesized class of models. This paper describes a test procedure for selecting the best model. The procedure is based on a synthesis of Bayesian and a cross-validation or sample reuse methodology that makes use of a one-at-a-time schema of observational omissions. Advantages of the test are argued on two grounds, and illustrative examples and simulation results are given.are given.

• Journal of the Korean Statistical Society
• /
• v.19 no.1
• /
• pp.24-44
• /
• 1990

The purpose of this paper is to extend the idea of Tamhane and Bechhofer (1977, 1979) concerning the normal means problem to some general class of distributions. The key idea in Tamhane and Bechhofer is the derivation of the computable lower bounds on the probability of a correct selection. To derive such lower bounds, they used the specific covariance structure of a multivariate normal distribution. It is shown that such lower bounds can be obtained for a class of stochastically increasing distributions under certain conditions, which is sufficiently general so as to include the normal means problem as a special application. As an application of the general theory to the scale parameters problem, a two-stage elimination type procedure for selecting the population associated with the smallest variance from among several normal populations is proposed. The design constants are tabulated and the relative efficiencies are computed.

• Journal of the Korean Statistical Society
• /
• v.16 no.2
• /
• pp.92-101
• /
• 1987

Our interest is to access in some way teh relative odds or probability that a multivariate observation Z belongs to one of k multivariate normal populations with unequal covariance matrices. We derived the empirical Bayes posterior odds ratio for the classification rule when population parameters are unknown. It is a generalization of the posterior odds ratio suggested by Gelsser (1964). The classification rule does not have complicated distribution theory which a large variety of techniques from the sampling viewpoint have. The proposed posterior odds ratio is compared to the Gelsser's posterior odds ratio through a Monte Carlo study. The results show that the empiricla Bayes posterior odds ratio, in general, performs better than the Gelsser's. Especially, for large dimension of Z and small training sample, the performance is prominent.

• Journal of the Korean Data and Information Science Society
• /
• v.24 no.1
• /
• pp.189-200
• /
• 2013

In this paper, it will be assumed that there are two distinct populations which are multivariate normal with equal covariance matrix. We also assume that the two populations are equally likely and the costs of misclassification are equal. The classification rule depends on the situation whether the training samples include missing values or not. We consider the conditional bootstrap confidence intervals for classification error rate when a block of observation is missing.

• Journal of Korean Society of Forest Science
• /
• v.103 no.2
• /
• pp.196-202
• /
• 2014

In order to select superior trees based on fruit characteristics and provide basic informations necessary for their improvement, total 107 individual trees of Sorbus alnifolia (Sieb. et Zucc.) K. Koch were selected from 11 wild populations in South Korea. After collecting normal fruit branch, we investigated morphological characteristics of fruit and then considered its relationship among the 11 populations by multivariate analysis method. Results from principal compound analysis showed that it represented 85.8% accumulated explanation from five principal compounds. According to cluster analysis based on fruit characteristics, the natural S. alnifolia populations were classified into four groups and Mt. Mani population was different from other populations. Selection effect with outstanding candidate trees including superior 5 individual trees (Gwangyo 1, Gwangyo 2, Deogyu 7, Mani 29, Mani 30) was estimated at 122.8%, 115.5% and 182.7% in fruit width, length and yield per fruit bunch, respectively. The object of this results will give us invaluable information about breeding by selection of S. alnifolia in south Korea.

• Journal of Preventive Medicine and Public Health
• /
• v.32 no.4
• /
• pp.513-525
• /
• 1999

Objectives : High-normal blood pressure' is a factor influencing decision to initiate targeted intensive intervention strategy in westernized populations. JNC-VI offered the vigorous lifestyle modification for persons with 'high-normal blood pressure', who could be early detected. As a hypertension seems to be the result of multiple genetic factors operating in concert with associated environmental factors, it will be necessary to identify the high-normal blood pressure as a risk factor of hypertension for applying primary prevention strategy in Korean people. Methods : Although cohort study design might be adequate to recruit incidence cases, to keep time sequence of events, and to prevent information bias, nested case-control study was chosen for avoiding measurement errors because hypertension is a benign disease. Source population was the 'Seoul Cohort' participants and follow-up was done by using Korea Medical Insurance Corporation's database on the utilization of health services from 1 Jan93 to 30Jun97. Incidence cases were ascertained through the chart review, telephone contacts, and direct blood pressure measurements. Controls included the pairing of 4 individuals to each case on the basis of age. Results : As 75% of 247 incident cases had high-normal blood pressure, the crude odds ratio for hypertension was 2.04 (95% CI 1.47-2.83). Another statistically significant risk factors of hypertension were body mass index, dietary fiber, alcohol consumption, weekly activity and history of quitting smoking. The multivariate odds ratio of high-normal blood pressure adjusted for all risk factors was 1.84 (95% CI 1.31-2.56). Among high-normal blood pressure group, body mass index, weekly ethanol amounts, weekly physical activity, and dietary fiber except history of quitting smoking were still risk factors of hypertension. Conclusion : 'High-normal blood pressure' is a risk factor for hypertension in Korean middle-aged men, which represents that the vigorous lifestyle modification for persons with 'high-normal blood pressure' is need.

• Proceedings of the Korean Statistical Society Conference
• /
• 2003.05a
• /
• pp.85-90
• /
• 2003

In this paper we develop a method for finding optimal ordering of K statistical models. This is based on a dependent paired comparison experimental arrangement whose results can naturally be represented by a completely oriented graph (also so called tournament graph). Introducing preference probabilities, strong transitivity conditions, and an optimal criterion to the graph, we show that a Hamiltonian path obtained from row sum ranking is the optimal ordering. Necessary theories involved in the method and computation are provided. As an application of the method, generalized variances of K multivariate normal populations are compared by a Bayesian approach.

• Journal of Yeungnam Medical Science
• /
• v.22 no.2
• /
• pp.199-210
• /
• 2005

Background: The role of obesity in prostate cancer etiology remains controversial. The aim of this study was to evaluate the relationship between obesity and prostate cancer risk. Materials and methods: Between January 2000 and June 2005, 286 patients suspected of having prostate cancer underwent prostate biopsy. The clinical records of the 286 study patients were retrospectively reviewed with regard to age, Body Mass Index (BMI), serum PSA, TRUS, and prostate biopsy results. They were stratified by BMI into three groups according to the cutoffs recommended for Asian populations: normal, BMI less than 23 $kg/m^2$; overweight, BMI 23 to 25 $kg/m^2$; and obese, BMI greater than 25 $kg/m^2$. Results: As for BMIs, 132 (46.2%) were normal, 95 (33.2%) overweight and 59 (20.6%) were obese. A total of 99 (34.6%) patients were diagnosed as having prostate cancer. In multivariate logistic regression analyses, no significant association was observed between BMI and prostate cancer detection. Conclusion: We initially hypothesized that obesity may be biologically associated with increased prostate cancer development. However, our study did not show a significant association between BMI and prostate cancer.