• 응용통계연구
• /
• 제24권6호
• /
• pp.1149-1160
• /
• 2011

기존의 frequentist 추론에 비해 Bayesian 추론에서의 가설 검정 및 모형 선택 문제는 학자들 간에 일치된 견해를 보이지 못하고 있으며 아직도 논란이 되는 것들이 많다. Bayesian 추론에서 가설 검정 및 모형 선택의 기준으로 널리 쓰이는 Bayes factor는 이해하기 쉬우나 여러 경우에 구하기 어려운 단점이 존재한다. 그 외에 다른 기준으로 Spiegelhalter 등 (2002)가 제시한 DIC(Deviance Information Criterion)과 frequentist 추론에서의 P-value에 대비되는 Bayesian P-value가 있다. 본 논문에서는 Swiss banknote 자료를 Bayesian 로지스틱 회귀모형으로 분석하고 관련 기준들을 구하여 각 기준들이 일관성 있는 결론을 보이는지 확인하고자 한다.

• Journal of the Korean Data and Information Science Society
• /
• 제27권5호
• /
• pp.1225-1239
• /
• 2016

We investigate pediatric tumor incidence data collected by the Florida Association for Pediatric Tumor program using various models commonly used in disease mapping analysis. Particularly, we consider Poisson normal models with various conditional autoregressive structure for spatial dependence, a zero-in ated component to capture excess zero counts and a spatio-temporal model to capture spatial and temporal dependence, together. We found that intrinsic conditional autoregressive model provides the smallest Deviance Information Criterion (DIC) among the models when only spatial dependence is considered. On the other hand, adding an autoregressive structure over time decreases DIC over the model without time dependence component. We adopt weighted ranks squared error loss to identify high risk regions which provides similar results with other researchers who have worked on the same data set (e.g. Zhang et al., 2014; Wang and Rodriguez, 2014). Our results, thus, provide additional statistical support on those identied high risk regions discovered by the other researchers.

• Journal of the Korean Data and Information Science Society
• /
• 제25권1호
• /
• pp.187-194
• /
• 2014

We consider a Bayesian nonignorable selection model to accommodate the selection bias. Markov chain Monte Carlo methods is known to be very useful to fit the nonignorable selection model. However, sensitivity to prior assumptions on parameters for selection mechanism is a potential problem. To quantify the sensitivity to prior assumption, the deviance information criterion and the conditional predictive ordinate are used to compare the goodness-of-fit under two different prior specifications. It turns out that the 'MLE' prior gives better fit than the 'uniform' prior in viewpoints of goodness-of-fit measures.

• 응용통계연구
• /
• 제33권1호
• /
• pp.47-59
• /
• 2020

본 논문에서는 마코프 이항 회귀 모형의 시차가 알려져 있거나 그렇지 않은 경우일 때, t-링크 함수를 갖는 종단적 마코프 이항 회귀 모형을 제시한다. 일반적으로, 이항 회귀 모형에서는 로직 모형이나 프로빗 모형이 주로 사용된다. t-링크 함수는 t 분포가 자유도가 커질수록 정규분포로 근사하기 때문에 프로빗 모형을 대신 더 많은 유연성을 위해 사용될 수 있다. 게다가 마코프 회귀모형은 종단 자료에 대해 사용될 수 있다. 우리는 마코프 회귀 모형의 시차를 결정하기 위해 베이지안 방법을 제시하고자 한다. 특히, 각 모델의 차수에 대해 알고 있는 경우에는 DIC를 기준으로 모델 비교를 실시하였다. 모델의 차수에 대해 모르는 경우에는 가능한 모델들의 사후 확률을 이용하였다. 복잡한 베이지안 계산을 해결하기 위하여 Albert와 Chib (1993), Kuo와 Mallick (1998)과 Erkanli 등 (2001)의 방법을 이용하여 모델을 재설정하였다. 제안하는 방법은 시뮬레이션 데이터와 Somer 등 (1984)에 의해 조사된 인도네시아 어린이 종단 데이터에 적용했다. 마코프 이항 회귀모형의 순서에 대해서 아는 경우와 모르는 경우를 각각 가정하여 최적의 모델을 알아보기 위해 MCMC 방법을 사용하였다. 또한, 매트로폴리스 해스팅 알고리즘의 수렴성을 점검하기 위해 Gelman과 Rubin의 진단을 이용했다.

• Management Science and Financial Engineering
• /
• 제12권2호
• /
• pp.19-35
• /
• 2006

We use the hierarchical Bayesian approach to describe the transition probabilities of a binary nonhomogeneous Markov chain. The Markov chain is used for describing the transition behavior of emotionally disturbed children in a treatment program. The effects of covariates on transition probabilities are assessed using a logit link function. To describe the time evolution of transition probabilities, we consider two modeling strategies. The first strategy is based on the concept of exchangeabiligy, whereas the second one is based on a first order Markov property. The deviance information criterion (DIC) measure is used to compare models with two different time dependent structures. The inferences are made using the Markov chain Monte Carlo technique. The developed methodology is applied to some real data.

• Communications for Statistical Applications and Methods
• /
• 제29권1호
• /
• pp.65-83
• /
• 2022

Although various statistical methods have been developed to map time-dependent genetic factors, most identified genetic variants can explain only a small portion of the estimated genetic variation in longitudinal traits. Gene-gene and gene-time/environment interactions are known to be important putative sources of the missing heritability. However, mapping epistatic gene-gene interactions is extremely difficult due to the very large parameter spaces for models containing such interactions. In this paper, we develop a Gaussian process (GP) based nonparametric Bayesian variable selection method for longitudinal data. It maps multiple genetic markers without restricting to pairwise interactions. Rather than modeling each main and interaction term explicitly, the GP model measures the importance of each marker, regardless of whether it is mostly due to a main effect or some interaction effect(s), via an unspecified function. To improve the flexibility of the GP model, we propose a novel grid-based method for the within-subject dependence structure. The proposed method can accurately approximate complex covariance structures. The dimension of the covariance matrix depends only on the number of fixed grid points although each subject may have different numbers of measurements at different time points. The deviance information criterion (DIC) and the Bayesian predictive information criterion (BPIC) are proposed for selecting an optimal number of grid points. To efficiently draw posterior samples, we combine a hybrid Monte Carlo method with a partially collapsed Gibbs (PCG) sampler. We apply the proposed GP model to a mouse dataset on age-related body weight.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권9호
• /
• pp.4049-4054
• /
• 2014

Background: Race and ethnicity are significant factors in predicting survival time of breast cancer patients. In this study, we applied advanced statistical methods to predict the survival of White non-Hispanic female breast cancer patients, who were diagnosed between the years 1973 and 2009 in the United States (U.S.). Materials and Methods: Demographic data from the Surveillance Epidemiology and End Results (SEER) database were used for the purpose of this study. Nine states were randomly selected from 12 U.S. cancer registries. A stratified random sampling method was used to select 2,000 female breast cancer patients from these nine states. We compared four types of advanced statistical probability models to identify the best-fit model for the White non-Hispanic female breast cancer survival data. Three model building criterion were used to measure and compare goodness of fit of the models. These include Akaike Information Criteria (AIC), Bayesian Information Criteria (BIC), and Deviance Information Criteria (DIC). In addition, we used a novel Bayesian method and the Markov Chain Monte Carlo technique to determine the posterior density function of the parameters. After evaluating the model parameters, we selected the model having the lowest DIC value. Using this Bayesian method, we derived the predictive survival density for future survival time and its related inferences. Results: The analytical sample of White non-Hispanic women included 2,000 breast cancer cases from the SEER database (1973-2009). The majority of cases were married (55.2%), the mean age of diagnosis was 63.61 years (SD = 14.24) and the mean survival time was 84 months (SD = 35.01). After comparing the four statistical models, results suggested that the exponentiated Weibull model (DIC= 19818.220) was a better fit for White non-Hispanic females' breast cancer survival data. This model predicted the survival times (in months) for White non-Hispanic women after implementation of precise estimates of the model parameters. Conclusions: By using modern model building criteria, we determined that the data best fit the exponentiated Weibull model. We incorporated precise estimates of the parameter into the predictive model and evaluated the survival inference for the White non-Hispanic female population. This method of analysis will assist researchers in making scientific and clinical conclusions when assessing survival time of breast cancer patients.

• Asian Pacific Journal of Cancer Prevention
• /
• 제17권1호
• /
• pp.361-367
• /
• 2016

We have reported a high prevalence of breast cancer in light-polluted areas in Korea. However, it is necessary to analyze the spatial effects of light polluted areas on breast cancer because light pollution levels are correlated with region proximity to central urbanized areas in studied cities. In this study, we applied a spatial regression method (an intrinsic conditional autoregressive [iCAR] model) to analyze the relationship between the incidence of breast cancer and artificial light at night (ALAN) levels in 25 regions including central city, urbanized, and rural areas. By Poisson regression analysis, there was a significant correlation between ALAN, alcohol consumption rates, and the incidence of breast cancer. We also found significant spatial effects between ALAN and the incidence of breast cancer, with an increase in the deviance information criterion (DIC) from 374.3 to 348.6 and an increase in $R^2$ from 0.574 to 0.667. Therefore, spatial analysis (an iCAR model) is more appropriate for assessing ALAN effects on breast cancer. To our knowledge, this study is the first to show spatial effects of light pollution on breast cancer, despite the limitations of an ecological study. We suggest that a decrease in ALAN could reduce breast cancer more than expected because of spatial effects.

• 한국수자원학회논문집
• /
• 제55권12호
• /
• pp.1137-1147
• /
• 2022

하천수위와 지하수위는 수문학적 순환과정에서 나타나는 수문학적 요소로 상호 연관성이 높으며 이러한 수문학적 요소에 대해 확률적 시뮬레이션을 독립적으로 수행하는 경우 상호 관련 정보손실과 같은 문제가 발생할 수 있다. 하천수위와 지하수위는 수문학적·농업적 가뭄을 평가하는 중요한 지표로 활용되지만 하천수위의 경우 건기 중에는 정확한 관측을 얻기가 매우 어려우며, 지하수위의 경우 데이터 기간이 상대적으로 짧아 이를 활용한 가뭄지수 사용이 제한적이다. 이와 관련하여 손실 없이 자료를 최대한 이용하기 위해 본 연구는 각 변수의 시간 의존성을 고려하는 동시에 상호 연관된 변수의 시간 의존성을 고려하는 벡터자기회 모형VAR)을 구성했다. 하천수위와 지하수위 사이의 자기 상관 및 상관관계를 확인하고, 정보 손실을 최소화하는 하천수위 및 지하수위를 예측할 수 있는지 여부를 결정하기 위해 벡터 자기 회귀 모델의 최적 순서 결정과 매개변수를 결정하였다. 또한, 두 변수 간의 상관관계를 반영하지 않는 자기회귀모형(AR)을 구축하고 모의에 대한 DIC와 상관계수를 VAR 모형과 비교하여 VAR 모형 더 적합함을 보이고 하천수위와 지하수위의 간의 상호관계성을 효과적으로 반영함을 확인하였다.

• 한국물환경학회지
• /
• 제29권6호
• /
• pp.832-841
• /
• 2013

In recent years, eutrophication in the Paldang Lake has become one of the major environmental problems in Korea as it may threaten drinking water safety and human health. Thus it is important to understand the phenomena and predict the time and magnitude of algal blooms for applying adequate algal reduction measures. This study performed seasonal water quality assessment and chlorophyll-a prediction using Bayseian simple/multiple linear regression analysis. Bayseian regression analysis could be a useful tool to overcome limitations of conventional regression analysis. Also it can consider uncertainty in prediction by using posterior distribution. Generally, chlorophyll-a of a P2(Paldang Dam 2) site showed high concentration in spring and it was similar to that of P4(Paldang Dam 4) site. For the development of Bayseian model, we performed seasonal correlation. As a result, chlorophyll-a of a P2 site had a high correlation with P5(Paldang Dam 5) site in spring (r = 0.786, p<0.05) and with P4 in winter (r = 0.843, p<0.05). Based on the DIC (Deviance Information Criterion) value, critical explanatory variables of the best fitting Bayesian linear regression model were selected as a $PO_4-P$ (P2), Chlorophyll-a (P5) in spring, $NH_3-N$ (P2), Chlorophyll-a (P4), $NH_3-N$ (P4) in summer, DTP (P2), outflow (P2), TP (P3), TP (P4) fall, COD (P2), Chl-a (P4) and COD (P4) in winter. The results of chlorophyll-a prediction showed relatively high $R^2$ and low RMSE values in summer and winter.