• Journal of the Korean Statistical Society
• /
• v.29 no.2
• /
• pp.231-245
• /
• 2000

This paper considers a linear regression model with space and time data in where the disturbances follow spatially correlated error components. We provide the best linear unbiased predictor for the one way error components. We provide the best linear unbiased predictor for the one way error component model with spatial autocorrelation. Further, we derive two diagnostic test statistics for the assessment of model specification due to spatial dependence and random effects as an application of the Lagrange Multiplier principle.

• Communications for Statistical Applications and Methods
• /
• v.16 no.6
• /
• pp.971-978
• /
• 2009

Poisson generalized linear mixed models(GLMMs) have been widely used for the analysis of clustered or correlated count data. For the inference marginal likelihood, which is obtained by integrating out random effects is often used. It gives maximum likelihood(ML) estimator, but the integration is usually intractable. In this paper, we propose how to obtain the ML estimator via Laplace approximation based on hierarchical-likelihood (h-likelihood) approach under the Poisson GLMMs. In particular, the h-likelihood avoids the integration itself and gives a statistically efficient procedure for various random-effect models including GLMMs. The proposed method is illustrated using two practical examples and simulation studies.

• Structural Engineering and Mechanics
• /
• v.20 no.3
• /
• pp.293-312
• /
• 2005

In this paper, free vibration of rotating beam with random properties is studied. The cross-sectional area, elasticity modulus, moment of inertia, shear modulus and density are modeled as random fields and the rotational speed as a random variable. To study uncertainty, stochastic finite element method based on second order perturbation method is applied. To discretize random fields, the three methods of midpoint, interpolation and local average are applied and compared. The effects of rotational speed, setting angle, random property variances, discretization scheme, number of elements, correlation of random fields, correlation function form and correlation length on "Coefficient of Variation" (C.O.V.) of first mode eigenvalue are investigated completely. To determine the significant random properties on the variation of first mode eigenvalue the sensitivity analysis is performed. The results are studied for both Timoshenko and Bernoulli-Euler rotating beam. It is shown that the C.O.V. of first mode eigenvalue of Timoshenko and Bernoulli-Euler rotating beams are approximately identical. Also, compared to uncorrelated random fields, the correlated case has larger C.O.V. value. Another important result is, where correlation length is small, the convergence rate is lower and more number of elements are necessary for convergence of final response.

• Journal of the Korean Data and Information Science Society
• /
• v.19 no.4
• /
• pp.1327-1334
• /
• 2008

Mixed effect binomial regression models are widely used for analysis of correlated count data in which the response is the result of a series of one of two possible disjoint outcomes. In this paper, we consider kernel extensions with nonparametric fixed effects and parametric random effects. The estimation is through the penalized likelihood method based on kernel trick, and our focus is on the efficient computation and the effective hyperparameter selection. For the selection of hyperparameters, cross-validation techniques are employed. Examples illustrating usage and features of the proposed method are provided.

• Asian-Australasian Journal of Animal Sciences
• /
• v.15 no.7
• /
• pp.925-931
• /
• 2002

Gibbs sampling algorithms were implemented to the multi-trait threshold animal models with any combinations of multiple binary, ordered categorical, and linear traits and investigate the amount of bias on these models with two kinds of parameterization and algorithms for generating underlying liabilities. Statistical models which included additive genetic and residual effects as random and contemporary group effects as fixed were considered on the models using simulated data. The fully conditional posterior means of heritabilities and genetic (residual) correlations were calculated from 1,000 samples retained every 10th samples after 15,000 samples discarded as "burn-in" period. Under the models considered, several combinations of three traits with binary, multiple ordered categories, and continuous were analyzed. Five replicates were carried out. Estimates for heritabilities and genetic (residual) correlations as the posterior means were unbiased when underlying liabilities for a categorical trait were generated given by underlying liabilities of the other traits and threshold estimates were rescaled. Otherwise, when parameterizing threshold of zero and residual variance of one for binary traits, heritability estimates were inflated 7-10% upward. Genetic correlation estimates were biased upward if positively correlated and downward if negatively correlated when underling liabilities were generated without accounting for correlated traits on prior information. Residual correlation estimates were, consequently, much biased downward if positively correlated and upward if negatively correlated in that case. The more categorical trait had categories, the better mixing rate was shown.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.37 no.8
• /
• pp.48-56
• /
• 2000

Effects of the correlated random fluctuation in each grating half-period have been studied by an effective index transfer matrix method in quarter wavelength shifted DFB lasers. As the correlation coefficient changes from 0 to -1, single mode stability and wavelength accuracy are less degraded by the reduced error in the grating period. This fact shows that holographic grating fabrication is better than electron-beam lithography in discrete device fabrication provided that the magnitude of the random fluctuation is the same.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.4
• /
• pp.1083-1090
• /
• 2016

In clinical studies, different types of outcomes (e.g. repeated measures data and time-to-event data) for the same subject tend to be observed, and these data can be correlated. For example, a response variable of interest can be measured repeatedly over time on the same subject and at the same time, an event time representing a terminating event is also obtained. Joint modelling using a shared random effect is useful for analyzing these data. Inferences based on marginal likelihood may involve the evaluation of analytically intractable integrations over the random-effect distributions. In this paper we propose a joint HGLM approach for analyzing such outcomes using the HGLM (hierarchical generalized linear model) method based on h-likelihood (i.e. hierarchical likelihood), which avoids these integration itself. The proposed method has been demonstrated using various numerical studies.

• Communications for Statistical Applications and Methods
• /
• v.15 no.6
• /
• pp.1003-1011
• /
• 2008

Mixed-effect Poisson regression models are widely used for analysis of correlated count data such as those found in longitudinal studies. In this paper, we consider kernel extensions with semiparametric fixed effects and parametric random effects. The estimation is through the penalized likelihood method based on kernel trick and our focus is on the efficient computation and the effective hyperparameter selection. For the selection of hyperparameters, cross-validation techniques are employed. Examples illustrating usage and features of the proposed method are provided.

• Journal of Nutrition and Health
• /
• v.36 no.8
• /
• pp.870-881
• /
• 2003

We examined the effects of 5 g red pepper powder in soup preload given at breakfast on food intake, blood pressure, body core temperature, hunger, fullness and thirst scores in 29 female collage students. All subjects received two kind of soup preloads in random order. After ingesting a soup, subjects ate other food items as a breakfast ad libitum. Two soups were of the same composition and volume but differed only in 5 g red pepper. So one soup designated as "beef-vegetable" and the other soup designated as "red pepper". Red pepper soup consumption significantly enhanced energy and macronutrient intake by 17%. The hunger scores after test meals were inversely correlated with energy and nutrient intake in beef-vegetable meal. However, the postprandial hunger scores were not correlated with energy and nutrient intakes in red pepper meal. The fullness scores at 90 min after the red pepper meal were inversely correlated with energy and nutrient intake whereas the fullness scores after beef-vegetable meal were not correlated with energy and nutrient intake. These results suggest that hot red pepper ingestion may desensitize some gastrointestinal vagal afferents and disturb feeling of hunger and fullness. The postprandial changes of body temperatures in red pepper meal were higher for a longer time in comparison with those in beef-vegetable meal. For the red pepper meal there frequently were higher correlations between blood pressures and anthropometric measurements, compared to those in beef-vegetable meal. These results might be explained partly by the enhancing effects of capsaicin on thermogenesis and sympathetic nervous system activity. It is concluded that the ingestion of spicy soup with red pepper can increase appetite, energy and nutrient intakes in Korean females, and this effect might be related to disturbed feeling of hunger and fullness.hunger and fullness.

• The Korean Journal of Applied Statistics
• /
• v.21 no.6
• /
• pp.923-932
• /
• 2008

We are likely to face complex multivariate data which can be characterized by having a non-trivial correlation structure. For instance, omitted covariates may simultaneously affect more than one count in clustered data; hence, the modeling of the correlation structure is important for the efficiency of the estimator and the computation of correct standard errors, i.e., valid inference. A standard way to insert dependence among counts is to assume that they share some common unobservable variables. For this assumption, we fitted correlated random effect models considering multilevel model. Estimation was carried out by adopting the semiparametric approach through a finite mixture EM algorithm without parametric assumptions upon the random coefficients distribution.