• Communications for Statistical Applications and Methods
• /
• v.7 no.2
• /
• pp.533-540
• /
• 2000

The problem of information related to I poission experiments, each having a distinct failure rate $\theta$i I=1,2,…,I, is considered. Instead of using a standard exchangeable prior for $\theta$=($\theta$1,$\theta$2,…,$\theta$I), we consider a partition of the experiments and take the $\theta$i's belonging to the same partition subgroup to be exchangeable and the $\theta$i's belonging to distinct subgroups to be independent. And we perform Gibbs sampling approach for Bayesian inference on $\theta$ conditional on a partition. Numerical study using real data is provided.

• Communications for Statistical Applications and Methods
• /
• v.13 no.3
• /
• pp.491-501
• /
• 2006

We consider a multiple change point model with autoregressive conditional heteroscedasticity (ARCH). The model assumes that all or the part of the parameters in the ARCH equation change over time. The occurrence of the change points is modelled as the discrete time Markov process with unknown transition probabilities. The model is estimated by Markov chain Monte Carlo methods based on the approach of Chib (1998). Simulation is performed using a variant of perfect sampling algorithm to achieve the accuracy and efficiency. We apply the proposed model to the simulated data for verifying the usefulness of the model.

• Wind and Structures
• /
• v.9 no.3
• /
• pp.193-215
• /
• 2006

This paper presents an analysis of wind velocity measurements obtained from four ultrasonic anemometers arranged in a vertical formation. The anemometers were located in a rural environment with a view to providing detailed information on the flow statistics of the lower part of the atmospheric boundary layer, particularly for the extreme wind events that are important in loading calculations. The data is analysed using both conventional analysis and conditional sampling. The latter is combined with wavelet analysis in order to provide a detailed analysis of the energy/frequency relationship of the extreme events. The work presented in this paper suggests that on average the extreme events occur as a result of the superposition of two independent mechanisms - large scale events that scale on the atmospheric boundary layer thickness and small scale events a few tens of metres in size.

• Wind and Structures
• /
• v.4 no.2
• /
• pp.131-146
• /
• 2001

A full-scale synchronized data acquisition system was set up on the roof of the experimental building at the Texas Tech University Wind Engineering Research Field Laboratory to simultaneously collect approaching wind data, conical vortex images, and roof corner suction pressure data. One-second conditional sampling technique has been applied in the data analysis, which makes it possible to separately evaluate the influencing effects of the horizontal wind angle of attack, ${\theta}$, and the vertical wind angle of attack, ${\varphi}$. Results show a clear cause-and-effect relationship between the incident wind, conical vortices, and the induced roof-corner high-suction pressures. The horizontal wind angle of attack, ${\theta}$, is shown to be the most significant factor in influencing the overall vortex structure and the suction pressures beneath. It is further revealed that the vertical wind angle of attack, ${\varphi}$, plays a critical role in generating the instantaneous peak suction pressures near the roof corner.

• Communications for Statistical Applications and Methods
• /
• v.10 no.1
• /
• pp.19-30
• /
• 2003

Spatiotemporal statistical models are used for analyzing space-time data in many fields, such as environmental sciences, meteorology, geology, epidemiology, forestry, hydrology, fishery, and so on. It is well known that classical spatiotemporal process modeling requires the estimation of space-time variogram or covariance functions. In practice, the estimation of such variogram or covariance functions are computationally difficult and highly sensitive to data structures. We investigate a Bayesian hierarchical model which allows the specification of a more realistic series of conditional distributions instead of computationally difficult and less realistic joint covariance functions. The spatiotemporal model investigated in this study allows both spatial component and autoregressive temporal component. These two features overcome the inability of pure time series models to adequately predict changes in trends in individual sites.

• The Korean Journal of Applied Statistics
• /
• v.27 no.2
• /
• pp.263-275
• /
• 2014

The present study used a hierarchical Bayesian approach was used to develop a mixed effect model to describe the transitional behavior of subjects in time nonhomogeneous Markov chains. The posterior distributions of model parameters were not in analytically tractable forms; subsequently, a Gibbs sampling method was used to draw samples from full conditional posterior distributions. The proposed model was implemented with real data.

• The Korean Journal of Applied Statistics
• /
• v.9 no.1
• /
• pp.153-164
• /
• 1996

We discussed estimation of parameters using Gibbs sampler under order restriction on the parameters. Two well-knwon probability models, ordered exponential family and binomial distribution, are considered. We derived full conditional distributions(FCD) and also used one-for-one sampling algorithm to sample from the FCD's under order restrictions. Finally through two real data sets we compared three kinds of estimators; isotonic regression estimator, isotonic Bayesian estimator and the estimator using Gibbs sampler.

• Journal of the Korean Society of Safety
• /
• v.10 no.2
• /
• pp.39-45
• /
• 1995

Three-dimensional flow measurements were conducted between the rotors of the CRP To understand mean flow phenomena of the CRP's, the results of the three-dimensional measurements were shown. Interaction noise of the CRP, which increases the overall ,level of sound pressure In the new propulsion system, is documented by using the double conditional sampling technique. The rear rotor will increase the axial flow between the rotors of a CRP depending upon the relative locations between the forward and the rear rotor blades. The decay and spreading of the forward wakes and the upstream propagation of the rear blade disturbances are shown along with the interaction of the flow disturbances by the two rotors of blades.

• Journal of KIISE:Software and Applications
• /
• v.33 no.12
• /
• pp.1052-1061
• /
• 2006

This paper presents a method of using virtual examples to improve the classification accuracy for data with nominal attributes. Most of the previous researches on virtual examples focused on data with numeric attributes, and they used domain-specific knowledge to generate useful virtual examples for a particularly targeted learning algorithm. Instead of using domain-specific knowledge, our method samples virtual examples from a naive Bayesian network constructed from the given training set. A sampled example is considered useful if it contributes to the increment of the network's conditional likelihood when added to the training set. A set of useful virtual examples can be collected by repeating this process of sampling followed by evaluation. Experiments have shown that the virtual examples collected this way.can help various learning algorithms to derive classifiers of improved accuracy.

• The Korean Journal of Applied Statistics
• /
• v.28 no.2
• /
• pp.325-334
• /
• 2015

Elderly suicide rates tend to be high in Korea. Suicide by the elderly is no longer a personal problem; consequently, further research on risk and regional factors is necessary. Disease mapping in epidemiology estimates spatial patterns for disease risk over a geographical region. In this study, we use a simultaneous conditional autoregressive model for spatial correlations between neighboring areas to estimate standard mortality ratios and mapping. The method is illustrated with cause of death data from 2006 and 2010 to analyze regional patterns of elderly suicide in Korea. By considering spatial correlations, the Bayesian spatial models, mean educational attainment and percentage of the elderly who live alone was the significant regional characteristic for elderly suicide. Gibbs sampling and grid method are used for computation.