• The Korean Journal of Applied Statistics
• /
• v.28 no.2
• /
• pp.335-342
• /
• 2015

Joint hierarchical generalized linear models proposed by Molas et al. (2013) extend the simple longitudinal model into multiple models fitted jointly. It can easily handle the correlation of multivariate longitudinal data. In this paper, we apply this method to analyze KoGES cohort dataset. Fixed unknown parameters, random effects and variance components are estimated based on a standard framework of h-likelihood theory. Furthermore, based on the conditional Akaike information criterion the correlated covariance structure of random-effect model is selected rather than an independent structure.

• Water for future
• /
• v.28 no.5
• /
• pp.219-233
• /
• 1995

A non-stationary multivariate model is selected in which the mean and variance of rainfall are not temporally or spatially constant. And the rainfall prediction system is constructed which uses the recursive estimation algorithm, Kalman filter, to estimate system states and parameters of rainfall model simulataneously. The on-line, real-time, multivariate short-term, rainfall prediction for multi-stations and lead-times is carried out through the estimation of non-stationary mean and variance by the storm counter method, the normalized residual covariance and rainfall speed. The results of rainfall prediction system model agree with those generated by non-stationary multivariate model. The longer the lead time is, the larger the root mean square error becomes and the further the model efficiency decreases form 1. Thus, the accuracy of the rainfall prediction decreases as the lead time gets longer. Also it shows that the mean obtained by storm counter method constitutes the most significant part of the rainfall structure.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.1
• /
• pp.251-268
• /
• 1996

In this paper, a higher-order feedforward neural network called ridge polynomial network (RPN) which shows good approximation capability for nonlnear continuous functions defined on compact subsets in multi-dimensional Euclidean spaces, is presented. This network provides more efficient and regular structure as compared to ordinary higher-order feedforward networks based on Gabor-Kolmogrov polynomial expansions, while maintating their fast learning property. the ridge polynomial network is a generalization of the pi-sigma network (PSN) and uses a specialform of ridge polynomials. It is shown that any multivariate polynomial can be exactly represented in this form, and thus realized by a RPN. The approximation capability of the RPNs for arbitrary continuous functions is shown by this representation theorem and the classical weierstrass polynomial approximation theorem. The RPN provides a natural mechanism for incremental function approximation based on learning algorithm of the PSN. Simulation results on several applications such as multivariate function approximation and pattern classification assert nonlinear approximation capability of the RPN.

• 한국데이터정보과학회:학술대회논문집
• /
• 2003.10a
• /
• pp.57-72
• /
• 2003

This article provides integrated neural network models for the interest rate forecasting using change-point detection. The model is composed of three phases. The first phase is to detect successive structural changes in interest rate dataset. The second phase is to forecast change-point group with data mining classifiers. The final phase is to forecast the interest rate with BPN. Based on this structure, we propose three integrated neural network models in terms of data mining classifier: (1) multivariate discriminant analysis (MDA)-supported neural network model, (2) case based reasoning (CBR)-supported neural network model and (3) backpropagation neural networks (BPN)-supported neural network model. Subsequently, we compare these models with a neural network model alone and, in addition, determine which of three classifiers (MDA, CBR and BPN) can perform better. For interest rate forecasting, this study then examines the predictability of integrated neural network models to represent the structural change.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.2
• /
• pp.523-530
• /
• 2016

Most classical control charts assume that processes are serially independent, and autocorrelation among variables makes them unreliable. To address this issue, a variety of statistical approaches has been employed to estimate the serial structure of the process. In this paper, we propose a multioutput least squares support vector regression and apply it to construct a residual multivariate cumulative sum control chart for detecting changes in the process mean vector. Numerical studies demonstrate that the proposed multioutput least squares support vector regression based control chart provides more satisfying results in detecting small shifts in the process mean vector.

• Communications for Statistical Applications and Methods
• /
• v.13 no.3
• /
• pp.513-524
• /
• 2006

In this paper, we introduce a new notions of conditionally weak dependence and we study their properties, preservation of the conditionally weak independent and positive and negative quadrant dependent(CWQD) property under mixtures, limits, closure under convex combinations, and their interrelationships. Furthermore, we extend multivariate stochastic dependence to stronger conditions of dependence.

• Communications for Statistical Applications and Methods
• /
• v.8 no.3
• /
• pp.625-632
• /
• 2001

Principal component analysis(PCA) is a multivariate technique falling under the general title of factor analysis. The purpose of PCA is to Identify the dependence structure behind a multivariate stochastic observation In order to obtain a compact description of it. In engineering field PCA is utilized mainly (or data compression and restoration. In this paper we propose a new robust Hebbian algorithm for robust PCA. This algorithm is based on a hyperbolic tangent function due to Hampel ef al.(1989) which is known to be robust in Statistics. We do two experiments to investigate the performance of the new robust Hebbian learning algorithm for robust PCA.

• Journal of the Korean Data and Information Science Society
• /
• v.14 no.3
• /
• pp.641-651
• /
• 2003

This study suggests the hybrid models for interest rate forecasting using structural changes (or change points). The basic concept of this proposed model is to obtain significant intervals caused by change points, to identify them as the change-point groups, and to reflect them in interest rate forecasting. The model is composed of three phases. The first phase is to detect successive structural changes in the U. S. Treasury bill rate dataset. The second phase is to forecast the change-point groups with data mining classifiers. The final phase is to forecast interest rates with backpropagation neural networks (BPN). Based on this structure, we propose three hybrid models in terms of data mining classifier: (1) multivariate discriminant analysis (MDA)-supported model, (2) case-based reasoning (CBR)-supported model, and (3) BPN-supported model. Subsequently, we compare these models with a neural network model alone and, in addition, determine which of three classifiers (MDA, CBR and BPN) can perform better. For interest rate forecasting, this study then examines the prediction ability of hybrid models to reflect the structural change.

• Journal of the Korean Statistical Society
• /
• v.25 no.2
• /
• pp.255-263
• /
• 1996

Let $(X_{1j}, X_{2j}, … , X_{nj}, Y_j/)$j = 1, 2, … , n, be a sample of size n on an (m + l)-dimensional vector $(X_1, X_2, … , X_m, Y)$, m .geq. 1. If $Y_{(r)}$ denote the rth order statistic from Y, then the $X_{[r:n]}$ paired with $Y_(r)$ is termed the concomitant vector of the order statistics. The general distributions of concomitant of order statistics will be found. The mean, variance and covariance of$X_{[r:n]}$ Will be studied. Then we will apply the results to the multivariate normal variate case.e.

• Journal of the Korean Chemical Society
• /
• v.63 no.2
• /
• pp.78-84
• /
• 2019

High-resolution $^1H$ NMR spectroscopic technique has been widely used as one of the most powerful analytical tools in food chemistry as well as to define molecular structure. The $^1H$ NMR spectra-based metabolomics has focused on classification and chemometric analysis of complex mixtures. The principal component analysis (PCA), an unsupervised clustering method and used to reduce the dimensionality of multivariate data, facilitates direct peak quantitation and pattern recognition. Using a combination of these techniques, the various green teas and black teas brewed were investigated via metabolite profiling. These teas were characterized based on the leaf size and country of cultivation, respectively.