• Communications for Statistical Applications and Methods
• /
• v.31 no.3
• /
• pp.263-277
• /
• 2024

This paper proposes new parameterizations of the tilted beta binomial distribution, obtained from the combination of the binomial distribution and the tilted beta distribution, where the beta component of the mixture is parameterized as a function of their mean and variance. These new parameterized distributions include as particular cases the beta rectangular binomial and the beta binomial distributions. After that, we propose new linear regression models to deal with overdispersed binomial datasets. These new models are defined from the proposed new parameterization of the tilted beta binomial distribution, and assume regression structures for the mean and variance parameters. These new linear regression models are fitted by applying Bayesian methods and using the OpenBUGS software. The proposed regression models are fitted to a school absenteeism dataset and to the seeds germination rate according to the type seed and root.

• Proceedings of the KSPS conference
• /
• 2005.04a
• /
• pp.87-90
• /
• 2005

Today's state-of the-art speech recognition systems typically use continuous distribution hidden Markov models with the mixtures of Gaussian distributions. To obtain higher recognition accuracy, the hidden Markov models typically require huge number of Gaussian distributions. Such speech recognition systems have problems that they require too much memory to run, and are too slow for large applications. Many approaches are proposed for the design of compact acoustic models. One of those models is subspace distribution clustering hidden Markov model. Subspace distribution clustering hidden Markov model can represent original full-space distributions as some combinations of a small number of subspace distribution codebooks. Therefore, how to make the codebook is an important issue in this approach. In this paper, we report some experimental results on various quantization methods to make more accurate models.

• Journal of Korean Society of Water and Wastewater
• /
• v.21 no.1
• /
• pp.3-11
• /
• 2007

THM models have been developed in several researchers in order to better understand and manage the presence of THM in water distribution system. Several developed models were demonstrated in this study for estimating THM concentrations in target water distribution system. In order to investigate the performance of developed THM models, lab and field test were investigated. Predicted THM concentrations by all kind of models were showed good correlation with observed values. When the developed models were compared with lab and field test, the Rodriguez model during tested models was most predictive than the other models.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.39 no.3
• /
• pp.83-95
• /
• 1997

This study was conducted to derive optimal design floods by Gamma distribution models of the annual maximum series at eight watersheds along Geum , Yeong San and Seom Jin river Systems, Design floods obtained by different methods for evaluation of parameters and for plotting positions in the Gamma distribution models were compared by the relative mean errors and graphical fit along with 95% confidence interval plotted on Gamma probability paper. The results were analyzed and summarized as follows. 1.Adequacy for the analysis of flood flow data used in this study was confirmed by the tests of Independence, Homogeneity and detection of Outliers. 2.Basic statistics and parameters were calculated by Gamma distribution models using Methods of Moments and Maximum Likelihood. 3.It was found that design floods derived by the method of maximum likelihood and Hazen plotting position formular of two parameter Gamma distribution are much closer to those of the observed data in comparison with those obtained by other methods for parameters and for plotting positions from the viewpoint of relative mean errors. 4.Reliability of derived design floods by both maximum likelihood and method of moments with two parameter Gamma distribution was acknowledged within 95% confidence interval.

• Proceedings of the Korean Statistical Society Conference
• /
• 2003.10a
• /
• pp.161-166
• /
• 2003

In this paper, a new form of generalized linear models is proposed. The proposed models consist of a distribution function of the mean response and a weighted linear combination of distribution functions of covariates. This form addresses a structural problem of the link function in the generalized linear models. Markov chain Monte Carlo methods are used to estimate the parameters within a Bayesian framework.

• Proceedings of the KIEE Conference
• /
• 1998.07c
• /
• pp.1156-1158
• /
• 1998

This paper Presents two distribution-feeder models to simplify complicated distribution system calculations. These equivalent models are developed to simulate the total series voltage drop at the end of the given feeder and the total line loss of the given feeder accurately. In addition, the proposed models are bidirectional. This means that power infeed can be at either end and the model is accurate. Also, it is shown that the proposed models are suitable for network reconfiguration.

• Structural Engineering and Mechanics
• /
• v.80 no.5
• /
• pp.523-538
• /
• 2021

The mechanical behaviour and stability of coal mining engineering underground is significantly affected by ground water. In this study, nuclear magnetic resonance imaging (NMRI) technique was employed to determine the water distribution characteristics in coal specimens during saturation process, based on which the functional rule for water distribution was proposed. Then, using discrete element method (DEM), an innovative numerical modelling method was developed to simulate water-weakening effect on coal behaviour considering moisture content and water distribution. Three water distribution numerical models, namely surface-wetting model, core-wetting model and uniform-wetting model, were established to explore the water distribution influences. The feasibility and validity of the surface-wetting model were further demonstrated by comparing the simulation results with laboratory results. The investigation reveals that coal mechanical properties are affected by both water saturation coefficient and water distribution condition. For all water distribution models, micro-cracks always initiate and nucleate in the water-rich area and thus lead to distinct macro fracture characteristics. With the increase of water saturation coefficient, the failure of coal tends to be less violent with less cracks and ejected fragments. In addition, the core-wetting specimen is more sensitive to water than specimens with other water distribution models.

• Journal of the Korea Safety Management & Science
• /
• v.9 no.3
• /
• pp.165-171
• /
• 2007

Dependent models in quality statistics are classified as serially autocorrelated model, multivariate model and dependent sample model. Dependent sample model is most efficient in time and cost to obtain samples among the above models. This paper proposes to implement parametric and nonparametric models into production system depended on demand pattern. Nonparametric models have distribution free and asymptotic distribution free techniques. Quality statistical models are classified into two categories ; the number of dependent sample and the type of data. The type of data consists of nominal, ordinal, interval and ratio data. The number of dependent sample divides into 2 samples and more than 3 samples.

• Journal of Information Technology Applications and Management
• /
• v.28 no.4
• /
• pp.13-20
• /
• 2021

In this paper, I was applied the life distribution following linear failure rate distribution, Lindley distribution and Burr-Hatke exponential distribution extensively used in the arena of software reliability and were associated the reliability possessions of the software using the nonhomogeneous Poisson process with finite failure. Furthermore, the average value functions of the life distribution are non-increasing form. Case of the linear failure rate distribution (exponential distribution) than other models, the smaller the estimated value estimation error in comparison with the true value. In terms of accuracy, since Burr-Hatke exponential distribution and exponential distribution model in the linear failure rate distribution have small mean square error values, Burr-Hatke exponential distribution and exponential distribution models were stared as the well-organized model. Also, the linear failure rate distribution (exponential distribution) and Burr-Hatke exponential distribution model, which can be viewed as an effectual model in terms of goodness-of-fit because the larger assessed value of the coefficient of determination than other models. Through this study, software workers can use the design of mean square error, mean value function as a elementary recommendation for discovering software failures.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2006.04a
• /
• pp.725-732
• /
• 2006

This study has been started for the development of a refined live load distribution formula that has safety and precision toward I type prestressed concrete girder bridge. This type of bridge is mainly applied to short span bridges that are $25{\sim}40m$ in length. Based on various structure analysis models that are currently being applied as preceding studies for the development of live load distribution method. an analysis of flexural stiffness ratio for barrier and diaphragm has been performed. As the result of parametric analysis for the changes in flexural stiffness ratio, the effect of barrier on load distribution showed as insignificant in all structural analysis models while analyzing the deflection distribution. Also. the deflection distribution of the models with stiffness of 25% in which the diaphragm eccentricity is accounted for as same as the models with stiffness of 100% in which the diaphragm eccentricity is unaccounted for. This results are verified through the comparison with a experimental data.