• Communications for Statistical Applications and Methods
• /
• 제22권5호
• /
• pp.507-518
• /
• 2015

It is not easy to select a linear mixed model since the main interest for model building could be different and the number of parameters in the model could not be clearly defined. In this paper, performance of conditional Akaike Information Criteria and its bias-corrected version are compared with marginal Bayesian and Akaike Information Criteria through a simulation study. The results from the simulation study indicate that bias-corrected conditional Akaike Information Criteria shows promising performance when candidate models exclude large models containing the true model, but bias-corrected one prefers over-parametrized models more intensively when a set of candidate models increases. Marginal Bayesian and Akaike Information Criteria also have some difficulty to select the true model when the design for random effects is nested.

• Journal of the Korean Data and Information Science Society
• /
• 제12권1호
• /
• pp.19-25
• /
• 2001

Random effects models which describe the dependence via random effects in various correlated data have recently received considerable attention in the biomedical literature. They include mixed linear models (MLMs), generatized linear mixed models (GLMMS) and hierarchical generalized linear models (HGLMs). For the inference Lee and Nelder (2000) proposed the first-and second-order REML (restricted maximum likelihood) methods based on hierarchical-likelihood of tee and Welder (1996). In this paper, for Poisson-gamma HGLMs the new methods are theoretically compared with marginal likelihood methods and both methods are illustrated by two practical examples.

• Communications for Statistical Applications and Methods
• /
• 제29권5호
• /
• pp.513-532
• /
• 2022

In this paper, the use of Bayes factors and the deviance information criterion for model selection are compared in a Bayesian accelerated life testing setup. In Bayesian accelerated life testing, the most used tool for model comparison is the deviance information criterion. An alternative and more formal approach is to use Bayes factors to compare models. However, Bayesian accelerated life testing models with more than one stressor often have mathematically intractable posterior distributions and Markov chain Monte Carlo methods are employed to obtain posterior samples to base inference on. The computation of the marginal likelihood is challenging when working with such complex models. In this paper, methods for approximating the marginal likelihood and the application thereof in the accelerated life testing paradigm are explored for dual-stress models. A simulation study is also included, where Bayes factors using the different approximation methods and the deviance information are compared.

• 대한치과기공학회지
• /
• 제38권3호
• /
• pp.185-191
• /
• 2016

Purpose: The purpose of this study were to evaluate the quality of dental prostheses printed by 3-dimensional printing system. Methods: Mater model was prepared and ten study models were fabricated. Ten single crowns were printed by 3D-printing system(Resin group) and another ten single crowns using casting method were manufactured(Metal group). The marginal adaptation of single crowns were measured using by silicone replica technique. Silicone replicas were sectioned four times. The marginal adaptations were evaluated using by digital microscope. Statistical analyses were performed with Mann-Whitney test(${\alpha}=0.05$). Results: $Mean{\pm}standard$ deviations of all marginal adaptations were $92.1(20.0){\mu}m$ for Metal group and $69.7(12.3){\mu}m$ for Resin group. Two groups were no statistically significant differences(p>0.05). Conclusion: Marginal adaptation of single crowns printed by 3D-printing system were ranged within the clinical recommendation.

• Journal of the Korean Data and Information Science Society
• /
• 제26권1호
• /
• pp.141-150
• /
• 2015

로지스틱회귀에서 모형을 평가하거나 진단할 때 가설검정이 주로 사용되지만 이것만으로는 놓칠 수 있는 부분이 많고 이에 대한 보완을 위하여 그래픽적 방법의 사용이 요구된다. 그래프를 이용한 모형의 적절성 평가를 위한 도구로 잔차산점도가 널리 이용되고 있으나 적용 범위가 선형회귀에 국한되는 문제점이 있다. 해결 방안으로 주변모형산점도를 이용하여 모형의 적절성을 평가하는 방법이 있으나 역시 문제점을 가지고 있다. 본 논문에서는 주변모형산점도의 대안으로 카이잔차산점도를 제안하고 그 효용성을 알아본다.

• 한국통계학회:학술대회논문집
• /
• 한국통계학회 2003년도 춘계 학술발표회 논문집
• /
• pp.79-84
• /
• 2003

Likelihood estimation in random-effect models is often complicated because the marginal likelihood involves an analytically intractable integral. Numerical integration such as Gauss-Hermite quadrature is an option, but is generally not recommended when the dimensionality of the integral is high. An alternative is the use of hierarchical likelihood, which avoids such burdensome numerical integration. These two approaches for fitting binary data are compared and the advantages of using the hierarchical likelihood are discussed. Random-effect models for binary outcomes and for bivariate binary-continuous outcomes are considered.

• 대한수학회보
• /
• 제44권2호
• /
• pp.265-270
• /
• 2007

The modern approach for wavelets imposes a Bayesian prior model on the wavelet coefficients to capture the sparseness of the wavelet expansion. The idea is to build flexible probability models for the marginal posterior densities of the wavelet coefficients. In this note, we derive exact expressions for a popular model for the marginal posterior density.

• 대한치과기공학회지
• /
• 제36권3호
• /
• pp.159-164
• /
• 2014

Purpose: The purpose of this study was analysis of quality of fixed prostheses fabricated by dental CAD/CAM system. Methods: The ten same cases of stone models were manufactured by dental scannable model, and stone models were scanned using the dental scanner for changing digital model. Ten digital models were completed. The design of zirconia core for zirconia based all-ceramic crown was conducted by the dental CAD program. The samples were fabricated using the pre-sintered zirconia block by dental milling machine. Marginal gaps were analyzed using by silicone replica technique at the eight parts for quality analysis of samples. One-way ANOVA was used for statistical analysis(${\alpha}=0.05$). Results: The mean for marginal gaps were $93.2{\sim}99.1{\mu}m$ at the eight parts. One-was ANOVA didn't show significant differences(p=0.089). Conclusion: The fixed dental prostheses fabricated by dental CAD/CAM were within clinically acceptable range.

• 대한치과기공학회지
• /
• 제42권3호
• /
• pp.197-201
• /
• 2020

Purpose: This study aimed to assess the quality of dental prostheses printed by digital light-processing (DLP) technology. Methods: Ten experimental models were prepared. The ten specimens that were printed by DLP technology constituted the DLP group. The ten specimens that were produced in the same model by the casting method constituted the control group. The marginal gaps of the 20 specimens produced were measured. These gaps were measured by a silicon replica technique at two abutments of the specimen. Therefore, 20 marginal gaps were measured in each group. An independent sample t-test was performed to compare the marginal gaps measured in the two groups (α=0.05). Results: According to the results of the measurement, there was a significant difference between the mean marginal gap of the control group (78.8 ㎛) and that of the DLP group (91.5 ㎛), p<0.001. Conclusion: Although the mean marginal gaps of dental fixed prostheses produced by the DLP method was higher than the mean marginal gap of those produced by the casting method, it was considered to be within the clinical threshold value suggested by some previous studies.

• 대한치과기공학회지
• /
• 제42권3호
• /
• pp.228-233
• /
• 2020

Purpose: This study aimed to assess and compare the marginal fit of ceramic-based hybrid resin restoration (HYB) and zirconia restoration (ZIR) for dental computer-aided design/computer-aided manufacturing systems. Methods: A stainless steel master model was produced. The impression was first made with silicone, and then stone working models were produced. A total of twenty restorations were fabricated with two different materials: ZIR and HYB. The silicone film thickness of the marginal gap was measured using a digital microscope; digital photos were taken at a magnification of ×160, and then analyzed using a measurement software. The values of the result were evaluated with the independent-sample t-test (α=0.05). All statistical analyses were performed with a statistical software. Results: The mean values for the marginal gap was 37.14±2.96 ㎛ for HYB, compared with 40.37±5.26 ㎛ for ZIR. No significant difference was found between ZIR and HYB (p=0.107). Conclusion: As a result, the marginal fit of the restoration fabricated using the hybrid resin was better than that of the restoration fabricated using zirconia. Also, the marginal fit of all groups was below the clinical acceptable range of 120 ㎛. Thus, HYB for dental CAD/CAM system in this study is expected to be suitable for clinical use in dentistry.