• Communications for Statistical Applications and Methods
• /
• v.15 no.6
• /
• pp.969-976
• /
• 2008

Mixed linear models have been widely used in various correlated data including multivariate survival data. In this paper we extend hierarchical-likelihood(h-likelihood) approach for mixed linear models with right censored data to that for left censored data. We also allow a general random-effect structure and propose the estimation procedure. The proposed method is illustrated using a numerical data set and is also compared with marginal likelihood method.

• Proceedings of the Korean Statistical Society Conference
• /
• 2002.11a
• /
• pp.3-9
• /
• 2002

In financial time series, the autoregressive conditional heteroscedastic (ARCH) models have been widely used for modeling conditional variances. In many cases, non-normality or heavy-tailed distributions of the data have influenced the estimation methods under normality assumption. To solve this problem, a robust function for the conditional variances of the errors is proposed and compared the relative efficiencies of the estimators with other conventional models.

• Communications for Statistical Applications and Methods
• /
• v.8 no.3
• /
• pp.711-717
• /
• 2001

Two imperfect repair models for system are considered, one introduced by Brown and Proschan(1983) and the other by Lee and Seoh(1999). We, in this paper, after assigning repair costs to the system, optimize both repair models, when the underlying life distributions of the system are exponential, uniform and Weibull.

• Journal of the Korean Statistical Society
• /
• v.15 no.1
• /
• pp.46-61
• /
• 1986

Many procedures for deriving the Moore-Penrose invese $X^+$ have been developed, but the explicit forms of Moore-Penerose inverses for design matrices in analysis of variance models are not known heretofore. The purpose of this paper is to find explicit forms of $X^+$ for the one-way and the two-way analysis of variance models. Consequently, the Moore-Penerose inverse $X^+$ and the shortest solutions of them can be easily obtained to the level of pocket calculator by way of our results.

• Journal of the Korean Statistical Society
• /
• v.28 no.2
• /
• pp.183-193
• /
• 1999

In the problem of estimating estimable functions in classification linear models, we propose a method of obtaining least squares estimators of estimable functions. This method is based on the hierarchical Bayesian approach for estimating a vector of unknown parameters. Also, we verify that estimators obtained by our method are identical to least squares estimators of estimable functions obtained by using either generalized inverses or full rank reparametrization of the models. Some examples are given which illustrate our results.

• Journal of the Korean Statistical Society
• /
• v.28 no.2
• /
• pp.195-210
• /
• 1999

We consider a large class of exponential regression models with censored data and propose two modified Fisher scoring methods with corresponding algorithms. These proposed methods improve the Newton-Raphson method in estimating the model parameters. The simulated and real examples are illustrated in aspect of convergence.

• Communications for Statistical Applications and Methods
• /
• v.9 no.1
• /
• pp.115-128
• /
• 2002

Hierarchical models are widely used for inference on correlated parameters as a compromise between underfitting and overfilling problems. In this paper, we take a Bayesian approach to analyzing hierarchical models and suggest a Markov chain Monte Carlo methods to get around computational difficulties in Bayesian analysis of the hierarchical models. We apply the method to a real data on smoking and lung cancer which are collected from cities in China.

• Communications for Statistical Applications and Methods
• /
• v.13 no.1
• /
• pp.125-134
• /
• 2006

This study confirms that the regression model of endpoint of interval outputs is not identical with that of the other endpoint of interval outputs in interval regression models proposed by Tanaka et al. (1987) and constructs interval regression models using the best regression model given by variable selection. Also, this paper suggests a method to minimize the sum of lengths of a symmetric difference among observed and predicted interval outputs in order to estimate interval regression coefficients in the proposed model. Some examples show that the interval regression model proposed in this study is more accuracy than that introduced by Inuiguchi et al. (2001).

• Communications for Statistical Applications and Methods
• /
• v.7 no.3
• /
• pp.677-686
• /
• 2000

Outliers may occur with respect to any of the random components in mixed linear models. We develop a use of simple, inexpensive updating formulas to consider the effect of case-deletion for mixed linear models. The method described here requires inversions of an n x n matrix, where n is the number of nonempty cells. A numerical example illustrates the use of computational formulas.

• Journal of the Korean Statistical Society
• /
• v.21 no.1
• /
• pp.47-58
• /
• 1992

The autocorrelation function structures of bilinear time series model BL(p, q, r, s), $r \geq s$ are obtained and shown to be analogous to those of ARMA(p, l), l=max(q, s). Simulation studies are performed to investigate the adequacy of Akaike information criteria for identification between ARMA(p, l) and BL(p, q, r, s) models and for determination of orders of BL(p, q, r, s) models. It is suggested that the model of having minimum Akaike information criteria is selected for a suitable model.