• Communications for Statistical Applications and Methods
• /
• v.29 no.3
• /
• pp.333-351
• /
• 2022

The skew-t distribution is an attractive family of asymmetrical heavy-tailed densities that includes the normal, skew-normal and Student's-t distributions as special cases. In this work, we propose an EM-type algorithm for computing the maximum likelihood estimates for skew-t linear regression models with censored response. In contrast with previous proposals, this algorithm uses analytical expressions at the E-step, as opposed to Monte Carlo simulations. These expressions rely on formulas for the mean and variance of a truncated skew-t distribution, and can be computed using the R library MomTrunc. The standard errors, the prediction of unobserved values of the response and the log-likelihood function are obtained as a by-product. The proposed methodology is illustrated through the analyses of simulated and a real data application on Letter-Name Fluency test in Peruvian students.

• Journal of the Korean Data and Information Science Society
• /
• v.14 no.3
• /
• pp.441-450
• /
• 2003

Collaborative filtering is one of the most widely used methodologies for recommendation system. Collaborative filtering is based on a data matrix of each customer's preferences and frequently, there exits missing data problem. We introduced two imputation approach (multiple imputation via Markov Chain Monte Carlo method and multiple imputation via bootstrap method) to improve the prediction performance of collaborative filtering and evaluated the performance using EachMovie data.

• Proceedings of the Korean Institute of Industrial Safety Conference
• /
• 1997.11a
• /
• pp.117-122
• /
• 1997

This paper presents a study on the fuzzy based approach for the safety assessment of human body under ELF electric and magnetic(EM) field considering power system states. The analysis of ELF EM field based on quasi-static method is introduced. UP to the present, the analysis of ELF EM field has been conducted with the consideration of one transmission line, or a power line model only In this paper, however, the power system is included to model the expected and/or unexpected uncertainty caused by the load fluctuation and parameter changes and the states are classified into two types, normal state resulting from normal operation and emergency state from outages. In order to analyze the uncertainty in the normal state, the Monte Carlo Simulation, a statistic approach was introduced and line current and bus voltage distribution are calculated by a contingency analysis method, in the emergency state. To access the safety of human body, the approach based on fuzzy linguistic variable is adopted to overcome the shortcomings of the assessment by a crisp set concept. In order to validate the usefulness of the approach suggested herein, the case study using a sample system with 765(kV) was done. The results are presented and discussed.

• Nuclear Engineering and Technology
• /
• v.19 no.1
• /
• pp.10-21
• /
• 1987

Uncertainty analysis of the FLB accident is performed for KNU-1 using the response surface methodology and Monte Carlo simulation. The FLB analyses using the RELAP4/Mod6 were performed a number of times to generate the data base for the uncertainty analysis, along with the EM calculation for comparison purpose. Two kinds of input sets are utilized for response surface method to investigate and compare the effects of the uncertainty of input variables on the RCS peak pressure following a FLB. The first set is composed of six major plant operational parameters and the second set is composed of five major modelling parameters. It is found through the analysis of results that the uncertainties of modelling parameters have more influence on the RCS peak pressure than the uncertainties of plant operational parameters and that the extra margin of 9% of peak pressure is gained. And one of the assumptions of EM calculation, which is usually accepted as conservative is found to be erroneous, that is, the initial core inlet temperature is found to act negatively on the RCS pressure following a FLB.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.45-45
• /
• 2017

상이한 자연현상으로 발생된 자료들은 때때로 통계적으로 다른 특성을 가지는 경우가 있다. 이런 자료들은 다른 두 개 이상의 모집단에서 자료가 발생한 것으로 가정할 수 가 있다. 기존에 널리 사용되어온 분포형 모형의 경우 단일한 모집단으로부터 자료가 발생한다는 가정하에서 개발된 모형들로 위에서 언급한 자료들을 적절히 모의할 수 없다. 이런 상이한 모집단에서 발생된 자료를 모형화 하기 위해서 혼합분포모형(mixture distribution)이 개발되었다. 홍수나 가뭄 등과 같은 극치 사상의 경우 다양한 자연현상들로부터 발생하기에 혼합분포모형을 적용할 경우 보다 정확한 모의가 가능하다. 혼합분포모형은 두 개 이상의 비혼합분포모형들을 가중합하여 만들어진다. 혼합 분포모형의 형태로 인하여 기존의 분포형 모형의 매개변수 추정 모형으로 널리 사용되던 최우도법 (maximum likelihood method), 모멘트법(method of moment), 확률가중모멘트법 (probability weighted moment method) 등을 이용하여 혼합분포모형의 매개변수를 추정하는 것이 용이 하지 않다. 혼합분포모형의 매개변수 추정 방법으로는 Expectation-Maximization (EM) 알고리즘, Meta-Heuristic Maximum Likelihood (MHML) 방법, Markov Chain Monte Carlo (MCMC) 방법 등이 적용되고 있다. 현재까지 수자원 분야에서 사용되는 극치 자료를 혼합분포모형을 이용하여 모의할 때 매개변수 추정방법에 따른 특성에 대한 연구가 진행되지 않았다. 본 연구에서는 우리나라 연최대강우량 자료를 이용하여 혼합분포모형의 매개변수 추정방법 (EM 알고리즘, MHML 방법, MCMC 방법) 들의 특성들을 비교 분석하였다. 혼합분포모형으로는 Gumbel-Gumbel 혼합분포 모형을 적용하였다. 본 연구의 결과는 향후 혼합분포모형을 이용한 연구에 좋은 기초자료로 사용될 수 있을 것으로 판단된다.

• Communications for Statistical Applications and Methods
• /
• v.21 no.2
• /
• pp.147-160
• /
• 2014

In this paper, we introduce the exponentiated Weibull-geometric (EWG) distribution which generalizes two-parameter exponentiated Weibull (EW) distribution introduced by Mudholkar et al. (1995). This proposed distribution is obtained by compounding the exponentiated Weibull with geometric distribution. We derive its cumulative distribution function (CDF), hazard function and the density of the order statistics and calculate expressions for its moments and the moments of the order statistics. The hazard function of the EWG distribution can be decreasing, increasing or bathtub-shaped among others. Also, we give expressions for the Renyi and Shannon entropies. The maximum likelihood estimation is obtained by using EM-algorithm (Dempster et al., 1977; McLachlan and Krishnan, 1997). We can obtain the Bayesian estimation by using Gibbs sampler with Metropolis-Hastings algorithm. Also, we give application with real data set to show the flexibility of the EWG distribution. Finally, summary and discussion are mentioned.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.05
• /
• pp.279-282
• /
• 1997

Bayesian reconstruction methods for emission computed tomography have been a topic of interest in recent years, partly because they allow for the introduction of prior information into the reconstruction problem. Early formulations incorporated priors that imposed simple spatial smoothness constraints on the underlying object using Gibbs priors in the form of four-nearest or eight-nearest neighbors. While these types of priors, known as "membrane" priors, are useful as stabilizers in otherwise unstable ML-EM reconstructions, more sophisticated prior models are needed to model underlying source distributions more accurately. In this work, we investigate whether the "thin plate" model has advantages over the simple Gibbs smoothing priors mentioned above. To test and compare quantitative performance of the reconstruction algorithms, we use Monte Carlo noise trials and calculate bias and variance images of reconstruction estimates. The conclusion is that the thin plate prior outperforms the membrane prior in terms of bias and variance.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.19 no.3
• /
• pp.270-279
• /
• 2009

In order to check a necessity of health control for the laborers who are in use of mixed organic solvents in the printing industries, this study evaluated the use status of mixed organic solvents, health subjective symptoms on the exposure of the solvents, health hazard for each kind of printings for the employees who work for the printing industries located in Seoul and Gyeonggi. The study analyzed 228 sites and 311 people responded of the total 250 sites surveyed from March to September 2007, and obtained the following results; 1) Estimating the exposure of the mixed organic solvents, the study found that estimation of mixture(EM) was different for each kind of printings at a level of significance, excessiveness of EM was 7.5%, the highest, for gravure printing, 5.6% for screen printing, 4.7% for master printing, 2.9% for offset printing. 2) As to the mean scores of health subjective symptoms for each kind of printings, workers in screen printing showed high scores in every subjective symptom, of which symptom of central nervous system was 3.75, the highest, and the difference was statistically at a level of significance(p<0.01). 3) Results of the hazard analysis for carcinogens and non-carcinogens contained in the mixed organic solvents exposed to the workers showed that cancer risk of offset printing workers was $7.8{\times}10^{-9}$ for benzene, the mean cancer risk was $2.02.{\times}10^{-8}$ from Monte-Carlo simulation, and both risks did not exceed the US EPA permissible standard of $1{\times}10^{-6}$. The total hazard indices of the non-carcinogens estimated was 3.523, the highest, for gravure printing, 2.381 for master printing, 1.125 for screen printing, respectively, and all exceeded 1.

• Journal of Radiation Industry
• /
• v.5 no.4
• /
• pp.325-330
• /
• 2011

To predict the details of flow in industrial process unit, single photon emission computed tomography (SPECT) is a promising technique. Recently, industrial SPECT based on medical system has developed by researchers of the Korea Atomic Energy Research Institute (KAERI) and Hanyang University. In the present study, to confirm the effect of the number of detectors on image quality, and determine the optimal number of detectors in industrial SPECT, industrial SPECT system with various geometries were evaluated by the Monte Carlo simulation. CsI(Tl) detectors ($12mm{\times}12mm{\times}20mm$) with collimators (the geometric resolution of collimator $R_g$ was 4 cm at the center of the 30 cm diameter cylindrical vessel object) were modeled in a hexagonal array, and the point sources of $^{99m}Tc$, $^{68}Ga$, and $^{137}Cs$ were simulated at the center of the cylindrical vessel object using the MCNPX code. Then, the reconstruction images of each geometry were reconstructed using the expectation maximization (EM) algorithm. In this study, the reciprocity theorem was used to improve computation time required for system matrix of the EM algorithm. The result shows that the resolution of the reconstructed image was significantly improved by increasing the number of detectors in industrial SPECT system and more than 60 detectors will be required for the resolution of the reconstructed image.

• Communications for Statistical Applications and Methods
• /
• v.23 no.2
• /
• pp.131-146
• /
• 2016

In research on behavioral studies, significant attention has been paid to the stage-sequential process for longitudinal data. Latent class profile analysis (LCPA) is an useful method to study sequential patterns of the behavioral development by the two-step identification process: identifying a small number of latent classes at each measurement occasion and two or more homogeneous subgroups in which individuals exhibit a similar sequence of latent class membership over time. Maximum likelihood (ML) estimates for LCPA are easily obtained by expectation-maximization (EM) algorithm, and Bayesian inference can be implemented via Markov chain Monte Carlo (MCMC). However, unusual properties in the likelihood of LCPA can cause difficulties in ML and Bayesian inference as well as estimation in small samples. This article describes and addresses erratic problems that involve conventional ML and Bayesian estimates for LCPA with small samples. We argue that these problems can be alleviated with a small amount of prior input. This study evaluates the performance of likelihood and MCMC-based estimates with the proposed prior in drawing inference over repeated sampling. Our simulation shows that estimates from the proposed methods perform better than those from the conventional ML and Bayesian method.