• Communications for Statistical Applications and Methods
• /
• v.29 no.2
• /
• pp.239-250
• /
• 2022

In many applications, we frequently encounter correlated multiple outcomes measured on the same subject. Joint modeling of such multiple outcomes can improve efficiency of inference compared to independent modeling. For instance, in developmental toxicity studies, fetal weight and number of malformed pups are measured on the pregnant dams exposed to different levels of a toxic substance, in which the association between such outcomes should be taken into account in the model. The number of malformations may possibly have many zeros, which should be analyzed via zero-inflated count models. Motivated by applications in developmental toxicity studies, we propose a Bayesian joint modeling framework for continuous and count outcomes with excess zeros. In our model, zero-inflated Poisson (ZIP) regression model would be used to describe count data, and a subject-specific random effects would account for the correlation across the two outcomes. We implement a Bayesian approach using MCMC procedure with data augmentation method and adaptive rejection sampling. We apply our proposed model to dose-response analysis in a developmental toxicity study to estimate the benchmark dose in a risk assessment.

• Communications for Statistical Applications and Methods
• /
• v.31 no.5
• /
• pp.557-569
• /
• 2024

Based on the investigation of logistic regression models utilizing sparse triangulation within a compact domain in ℝ², this study addresses the limited research extending the triogram model to logistic regression. A primary challenge arises from the potential instability induced by a large number of vertices, hindering the effective modeling of complex relationships. To mitigate this challenge, we propose introducing sparsity to boundary vertices of the triangulation based on the Ramer-Douglas-Peucker algorithm and employing the K-means algorithm for adaptive vertex initialization. A second order coordinate-wise descent algorithm is adopted to implement the proposed method. Validation of the proposed algorithm's stability and performance assessment are conducted using synthetic and handwritten digit data (LeCun et al., 1989). Results demonstrate the advantages of our method over existing methodologies, particularly when dealing with non-rectangular data domains.

• Journal of Korean Society of Environmental Engineers
• /
• v.32 no.1
• /
• pp.47-52
• /
• 2010

Physical, chemical and biological properties of soils and cadmium(Cd) content of Artemisia princeps var. orientalis collected from 10 metalliferous mines were analysed. Cd contents of unplanted soils and rhizosphere soils were not significantly different(p < 0.05), and mean values were 5.92 and 5.91 mg/kg, respectively. In addition, Cd content of rhizosphere soils were correlated with Cd content of Artemisia princeps (p < 0.05, ${R^2}_{shoot}$ = 0.3120, ${R^2}_{root}$ = 0.4177). Minimum data set(MDS) of soil quality parameters for statistical assessment of Cd uptake was established by principal component analysis, and it was identified as organic matter(OM), dehydrogenase activity(DHA), pH, exchangeable Mg. According to multiple regression analysis using the MDS, coefficients of determination ($R^2$) for Cd uptake of shoot and root of Artemisia princeps were found to be 0.3418 and 0.5121, respectively. This suggests that statistical soil quality assessment using the MDS seems a useful tool to interpret heavy metal uptake of plant.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2008.04a
• /
• pp.145-150
• /
• 2008

This study proposes an improved AR-model based structural joint integrity monitoring method and a new damage sensitive feature using RMS values of impulse responses. The proposed methods were applied for joint integrity monitoring of a model scale 2-bay and 4-story steel frame structure and it was found that the AR coefficients could be more consistently estimated by adopting the band-pass filter and cross-correlation function to the raw acceleration signals and the joint damages could be successfully monitored by the proposed methods.

• 한국디지털정책학회:학술대회논문집
• /
• 2004.11a
• /
• pp.343-358
• /
• 2004

Many IT specialists say that ERP (Enterprise Resource Planning) is the best way to manage resources in enterprise effectively. Actually lots of companies are using ERP solutions in the hope of getting competitiveness and employing global standard business practice. Wishing to take advantage of ERP S/W, companies have a preference for purchasing it and outsourcing ERP project. This paper is focusing on ERP Package assessment model in business firms. This paper finds out what differences there are in purchasing ERP S/W for organization characteristics and building characteristics, and suggests some guidelines of S/W development to venders. The results would be strong implications for ERP vendors. Especially this paper identify what the reasons and the checkpoints are when firms introduce ERP S/W. To do this, this paper used empirical data obtained from companies in South Korea and analyzed it using statistical software.

• Journal of the Korean Home Economics Association
• /
• v.40 no.11
• /
• pp.119-130
• /
• 2002

This study investigated preschool children's script knowledge according to task situation and socioeconomic status. Subjects were seventy-eight 5-year-old children (38 low- and 40 middle-income children; 36 boys and 42 girls) recruited from three day-care centers in Seoul. Each child participated in the script knowledge assessment session. Assessment of script knowledge consisted of a picture-recognition and picture-sequencing task. Statistical methods used for data analysis were means, standard deviations, repeated measures ANOVA. Results showed that children's script knowledge scores were higher in familiar task situation than in unfamiliar task situation. Furthermore, middle-income children had higher scores of script knowledge than low-income children. Findings of this study indicate that there is the difference of script knowledge between low- and middle-income preschoolers.

• Journal of Environmental Impact Assessment
• /
• v.15 no.3
• /
• pp.193-206
• /
• 2006

Recently, high ozone episode occurred frequently in Korea. Moreover ozone episode occurred not only in the city but also in background area where local anthropogenic sources are not important. It analyzed frequency exceeding 100ppb ozone at air quality monitoring stations in Seoul and rural area during 1995-2004. This paper reports on the use of the Community Multiscale Air Quality (CMAQ) modelling system to predict hourly ozone levels. Domain resolutions of 30km, 10km, 3.333km (innermost) have been employed for this study. Summer periods in June 2004 have been simulated and the predicted results have been compared to data for metropolitan and rural air quality monitoring stations. The model performance has been evaluated with measured data through a range of statistical measures. Although, the CMAQ model reproduces the ozone temporal spatial trends it was not able to simulate the peak magnitudes consistently.

• Journal of Environmental Impact Assessment
• /
• v.20 no.1
• /
• pp.71-78
• /
• 2011

This paper aims to assessing impact of reduction of non-point source pollution in the Bokha Stream watershed. The BASINS/HSPF model was calibrated and verified for water flow and water qualities using Total Maximum Daily Load 8days data from 2006 to 2007. Accuracy of the BASINS/HSPF models in simulating hydrology and water quality was compared and there were somewhat differences of statistical results, but water flow and water quality were simulated in good conditions over the study period. The applicability of models was tested to evaluate non-point source control scenarios to response hydrology and water quality in the Bokha stream using various measures which include BMPs approach and change of landuse. The evaluation of reduction of non-point source pollution was developed using load-duration curve. Despite strong reduction of non-point source, there are not satiated target quality at low flow season.

• Journal of Environmental Impact Assessment
• /
• v.20 no.1
• /
• pp.37-48
• /
• 2011

Recently, the social and environmental functions of nature river are important due to the increase of expectation for river restoration. So it should be considered the effect of vegetation affecting the conveyance capacity and hydraulic resistance. However, it has not yet proposed a objective standard and modeling method to estimate the effect of conveyance capacity according to vegetaion distribution in the watercourse such as water level or velocity. Therefore, this study simulates the variations of water level and velocity using 3-dimensional hydrodynamic model, EFDC, to consider a conveyance capacity in downstream of the Soyang Reservoir. The simulation results were validated using statistical index such as F-test and T-test. As results, the water level rises about 0.01 to 0.47m and velocity difference are about -0.95m/s to 0.23m/s.

• New & Renewable Energy
• /
• v.6 no.2
• /
• pp.5-11
• /
• 2010

This paper reviews three commercial softwares for wind climate data analysis in wind resource assessment; WAsP/Observed Wind Climate, WindRose and Windographer. Windographer is evaluated as the best software because of its variety of input data format, analysis functions, easiness of user interface, etc. For a quantitative understanding of uncertainty depending on software selection, a benchmark is carried out with the met-mast observation dataset at the Gimnyeong Wind Turbine Performance Test Site. It is found that Weibull parameter calculation and air density correction have a dependency on the software so that such uncertainty should be considered when an analysis software is selected. It is confirmed that annual energy production calculated by WAsP using a statistical table of frequency of occurrence may have some error compared to a time-series calculation method used by the other softwares.