• Journal of the Korean Data and Information Science Society
• /
• v.17 no.3
• /
• pp.953-961
• /
• 2006

Let's say that we are given a k number of random variables following Poisson distribution that are individually dependent and which forms multivariate Poisson distribution. We particularly dealt with a method of creating random numbers that satisfies the covariance matrix, where the elements of covariance matrix are parameters forming a multivariate Poisson distribution. To create such random numbers, we propose a new algorithm based on the method reducing the number of parameter set and deal with its relationship to the Park et al.(1996) algorithm used in creating multivariate Bernoulli random numbers.

• ETRI Journal
• /
• v.43 no.4
• /
• pp.640-649
• /
• 2021

In this paper, an additional degree of freedom in phased multi-input multi-output (phased-MIMO) radar with any arbitrary desired covariance matrix is proposed using space-time codes. By using the proposed method, any desired transmit covariance matrix in MIMO radar (phased-MIMO radars) can be realized by employing fully correlated base waveforms such as phased-array radars and simply extending them to different time slots with predesigned phases and amplitudes. In the proposed method, the transmit covariance matrix depends on the base waveform and space-time codes. For simplicity, a base waveform can be selected arbitrarily (ie, all base waveforms can be fully correlated, similar to phased-array radars). Therefore, any desired covariance matrix can be achieved by using a very simple phased-array structure and space-time code in the transmitter. The main advantage of the proposed scheme is that it does not require diverse uncorrelated waveforms. This considerably reduces transmitter hardware and software complexity and cost. One the receiver side, multiple signals can be analyzed jointly in the time and space domains to improve the signal-to-interference-plus-noise ratio.

• Communications for Statistical Applications and Methods
• /
• v.21 no.2
• /
• pp.169-181
• /
• 2014

Marginalized random effects models (MREM) are commonly used to analyze longitudinal categorical data when the population-averaged effects is of interest. In these models, random effects are used to explain both subject and time variations. The estimation of the random effects covariance matrix is not simple in MREM because of the high dimension and the positive definiteness. A relatively simple structure for the correlation is assumed such as a homogeneous AR(1) structure; however, it is too strong of an assumption. In consequence, the estimates of the fixed effects can be biased. To avoid this problem, we introduce one approach to explain a heterogenous random effects covariance matrix using a modified Cholesky decomposition. The approach results in parameters that can be easily modeled without concern that the resulting estimator will not be positive definite. The interpretation of the parameters is sensible. We analyze metabolic syndrome data from a Korean Genomic Epidemiology Study using this method.

• The Korean Journal of Applied Statistics
• /
• v.17 no.1
• /
• pp.1-12
• /
• 2004

In this paper, we consider choosing the appropriate covariance structure for analyzing repeated measures data with three repeat factors from a study of blood pressure data, which is collected from the local residents of Yangpyeong, Gyeonggi-do (2001) and fitted linear mixed models to find the significant covariates on outcome variable(Blood Pressure)

• Journal of Intelligence and Information Systems
• /
• v.1 no.1
• /
• pp.91-109
• /
• 1995

This paper compared four knowledge acquisition methods (namely, neural network, case-based reasoning, discriminant analysis, and covariance structure modeling) for allergic rhinitis. The data were collected from 444 patients with suspected allergic rhinitis who visited the Otorlaryngology Deduring 1991-1993. Among four knowledge acquisition methods, the discriminant model had the best overall diagnostic capability (78%) and the neural network had slightly lower rate(76%). This may be explained by the fact that neural network is essentially non-linear discriminant model. The discriminant model was also most accurate in predicting allergic rhinitis (88%). On the other hand, the CSM had the lowest overall accuracy rate (44%) perhaps due to smaller input data set. However, it was most accuate in predicting non-allergic rhinitis (82%).

• Communications for Statistical Applications and Methods
• /
• v.22 no.4
• /
• pp.321-331
• /
• 2015

The K-means clustering algorithm is a popular and widely used method for clustering. For covariance matrices, we consider a geodesic clustering algorithm based on the K-means clustering framework in consideration of symmetric positive definite matrices as a Riemannian (non-Euclidean) manifold. This paper considers a geodesic clustering algorithm for data consisting of symmetric positive definite (SPD) matrices, utilizing the Riemannian geometric structure for SPD matrices and the idea of a K-means clustering algorithm. A K-means clustering algorithm is divided into two main steps for which we need a dissimilarity measure between two matrix data points and a way of computing centroids for observations in clusters. In order to use the Riemannian structure, we adopt the geodesic distance and the intrinsic mean for symmetric positive definite matrices. We demonstrate our proposed method through simulations as well as application to real financial data.

• Communications for Statistical Applications and Methods
• /
• v.31 no.1
• /
• pp.55-64
• /
• 2024

In this study, we consider the sample size determination problem for clustered count data with many zeros. In general, zero-inflated Poisson and binomial models are commonly used for zero-inflated data; however, in real data the assumptions that should be satisfied when using each model might be violated. We calculate the required sample size based on a discrete Weibull regression model that can handle both underdispersed and overdispersed data types. We use the Monte Carlo simulation to compute the required sample size. With our proposed method, a unified model with a low failure risk can be used to cope with the dispersed data type and handle data with many zeros, which appear in groups or clusters sharing a common variation source. A simulation study shows that our proposed method provides accurate results, revealing that the sample size is affected by the distribution skewness, covariance structure of covariates, and amount of zeros. We apply our method to the pancreas disorder length of the stay data collected from Western Australia.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.14 no.3
• /
• pp.463-472
• /
• 1994

A method of stochastic response analysis of base-isolated fluid-filled pool structures subject to random ground excitations is studied. Fluid-structure interaction effects between the flexible walls and contained fluid are taken into account in the form of added mass matrix derived by FEM modeling of the contained fluid motion. The stationary ground excitation is represented by Modified Clough-Penzien spectral model and the nonstationary one is obtained by imposing an envelope function on the stationary one. The stationary and nonstationary response statistics of the two different isolation systems are obtained by solving the governing Lyapunov covariance matrix differential equations.

• Journal of the Korean Data and Information Science Society
• /
• v.10 no.2
• /
• pp.369-385
• /
• 1999

For the growth curve model with arbitrary covariance structure, known as unstructured covariance matrix, the problems of detecting outliers are discussed in this paper. In order to detect outliers in the growth curve model, the likelihood ratio testing statistics in mean shift model is established and its distribution is derived. After we detected outliers in growth curve model, we test homo and/or hetero-geneous covariance matrices using PSR Quasi-Bayes Criterion. For illustration, one numerical example is discussed, which compares between before and after outlier deleting.

• Wind and Structures
• /
• v.18 no.1
• /
• pp.37-56
• /
• 2014

The evaluation of pressure fields acting on slender structures under wind loads is currently performed in experimental aerodynamic tests. For wind-sensitive structures, in fact, the knowledge of global and local wind actions is crucial for design purpose. This paper considers a particular slender structure under wind excitation, representative of most common high-rise buildings, whose experimental wind field on in-scale model was measured in the CRIACIV boundary-layer wind tunnel (University of Florence) for several angles of attack of the wind. It is shown that an efficient reduced model to represent structural response can be obtained by coupling the classical structural modal projection with the so called blowing modes projection, obtained by decomposing the covariance or power spectral density (PSD) wind tensors. In particular, the elaboration of experimental data shows that the first few blowing modes can effectively represent the wind-field when eigenvectors of the PSD tensor are used, while a significantly larger number of blowing modes is required when the covariance wind tensor is used to decompose the wind field.