• Journal of the Korean Operations Research and Management Science Society
• /
• v.26 no.1
• /
• pp.109-116
• /
• 2001

The detection of corporate failures is a subject that has been particularly amenable to cross-sectional financial ratio analysis. In most of firms, however, the financial data are available over past years. Because of this, a model utilizing these longitudinal data could provide useful information on the prediction of bankruptcy. To correctly reflect the longitudinal and firm-specific data, the generalized linear model with assuming the first order AR(autoregressive) process is proposed. The method is motivated by the clinical research that several characteristics are measured repeatedly from individual over the time. The model is compared with several other predictive models to evaluate the performance. By using the financial data from manufacturing corporations in the Korea Stock Exchange (KSE) list, we will discuss some experiences learned from the procedure of sampling scheme, variable transformation, imputation, variable selection, and model evaluation. Finally, implications of the model with repeated measurement and future direction of research will be discussed.

• International Journal of Control, Automation, and Systems
• /
• v.2 no.4
• /
• pp.516-522
• /
• 2004

In this paper we investigate the properties of a generalized impulse response Gramian. The recursive relationship satisfied by the family of Gramians is established. It is shown that the generalized impulse response Gramian contains information on the characteristic polynomial of a linear time-invariant continuous system. The results are applied to model reduction problem.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2006.11a
• /
• pp.373-376
• /
• 2006

In general, there are three kinds of methods in analyzing dynamic robust design experiment: loss model approach, response function approach, and response model approach. In this talk, we review the three modeling approaches in terms of several criteria in comparison. This talk also generalizes the response model approach based on a generalized linear model. We develop a generalized two-step optimization procedure to substantially reduce the process variance by dampening the effect of both explicit and hidden noise variables. The proposed method provides more reliable results through iterative modeling of the residuals from the fitted response model. The method is compared with three existing approaches in practical examples.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.2
• /
• pp.144-149
• /
• 2006

This paper deals with a balanced model reduction for uncertain nonlinear systems via T-S fuzzy approach. We define a generalized controllability/observability gramian and obtain a balanced state space model using generalized gramians which can be obtained from solutions of linear matrix inequalities. We present a balanced model reduction scheme by truncating not only state variables but also uncertain elements. An upper bound of the model reduction error will also be suggested. In order to demonstrate the efficacy of our method, a numerical example will be presented.

• The Korean Journal of Applied Statistics
• /
• v.30 no.5
• /
• pp.775-791
• /
• 2017

We frequently encounter binary data in real life. Logistic, Probit, Cauchit, Complementary log-log models are often used for binary data analysis. In order to analyze binary data, Liu (2004) proposed a Robit model, in which the inverse of cdf of the Student's t distribution is used as a link function. Kim et al. (2008) also proposed a generalized t-link model to make the binary regression model more flexible. The more flexible skewed distributions allow more flexible link functions in generalized linear models. In the sense, we propose a binary data regression model using skewed generalized t distributions introduced in Theodossiou (1998). We implement R code of the proposed models using the glm function included in R base and R sgt package. We also analyze Pima Indian data using the proposed model in R.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.5
• /
• pp.831-839
• /
• 2010

Least squares support vector machine (LS-SVM) is a kernel trick gaining a lot of popularities in the regression and classification problems. We use LS-SVM to propose a iterative algorithm for a nonlinear generalized autoregressive conditional heteroscedasticity model in the mean (GARCH-M) model to estimate the mean and the conditional volatility of stock market returns. The proposed method combines a weighted LS-SVM for the mean and unweighted LS-SVM for the conditional volatility. In this paper, we show that nonlinear GARCH-M models have a higher performance than the linear GARCH model and the linear GARCH-M model via real data estimations.

• The Korean Journal of Applied Statistics
• /
• v.30 no.6
• /
• pp.957-981
• /
• 2017

A generalized linear mixed model is an extension of a generalized linear model that allows random effect as well as provides flexibility in developing a suitable model when observations are correlated or when there are other underlying phenomena that contribute to resulting variability. We describe maximum likelihood estimation methods for logistic regression models that include random effects - the Laplace approximation, Gauss-Hermite quadrature, adaptive Gauss-Hermite quadrature, and pseudo-likelihood. Applications are provided with social science problems by analyzing the effect of mental health and life satisfaction on volunteer activities from Korean welfare panel data; in addition, we observe that the inclusion of random effects in the model leads to improved analyses with more reasonable inferences.

• The Korean Journal of Applied Statistics
• /
• v.25 no.6
• /
• pp.1037-1047
• /
• 2012

The generalized linear mixed model(GLMM) is widely used in fitting categorical responses of clustered data. In the numerical approximation of likelihood function the normality is assumed for the random effects distribution; subsequently, the commercial statistical packages also routinely fit GLMM under this normality assumption. We may also encounter departures from the distributional assumption on the response variable. It would be interesting to investigate the impact on the estimates of parameters under misspecification of distributions; however, there has been limited researche on these topics. We study the sensitivity or robustness of the maximum likelihood estimators(MLEs) of GLMM for counts data when the true underlying distribution is normal, gamma, exponential, and a mixture of two normal distributions. We also consider the effects on the MLEs when we fit Poisson-normal GLMM whereas the outcomes are generated from the negative binomial distribution with overdispersion. Through a small scale Monte Carlo study we check the empirical coverage probabilities of parameters and biases of MLEs of GLMM.

• Journal of Korean Society for Quality Management
• /
• v.24 no.2
• /
• pp.128-141
• /
• 1996

The advent of the quality-improvement movement caused a great expansion in the use of statistically designed experiments in industry. The regression method is often used for the analysis of data from such experiments. However, the data for a quality characterstic often takes the form of counts or the ratio of counts, e.g. fraction of defectives. For such data the analysis using generalized linear models is preferred to that using the simple regression model. In this paper we introduce the generalized linear model and show how it can be used for the analysis of non-normal data from quality-improvement experiments.

• Proceedings of the Safety Management and Science Conference
• /
• 2009.04a
• /
• pp.423-427
• /
• 2009

This study proposes the generation mechanism of various design matrix using generalized linear model for design of experiment. Design generation method of GLM analysis, factorial design(FD) with center points, ANOVA design with lack-of-fit test, and response surface design are introduced. In central composite(CC) design, orthogonal blocking and fractional factorial design(FFD) are presented. We compare the design of Box-Benhken(BB) and face-centred central compsite design.