• Communications for Statistical Applications and Methods
• /
• 제23권6호
• /
• pp.445-466
• /
• 2016

Nonparametric Bayesian methods have seen rapid and sustained growth over the past 25 years. We present a gentle introduction to the methods, motivating the methods through the twin perspectives of consistency and false consistency. We then step through the various constructions of the Dirichlet process, outline a number of the basic properties of this process and move on to the mixture of Dirichlet processes model, including a quick discussion of the computational methods used to fit the model. We touch on the main philosophies for nonparametric Bayesian data analysis and then reanalyze a famous data set. The reanalysis illustrates the concept of admissibility through a novel perturbation of the problem and data, showing the benefit of shrinkage estimation and the much greater benefit of nonparametric Bayesian modelling. We conclude with a too-brief survey of fancier nonparametric Bayesian methods.

• Communications for Statistical Applications and Methods
• /
• 제31권3호
• /
• pp.323-336
• /
• 2024

The accurate forecasting of insurance claims is a critical component for insurers' risk management decisions. Hierarchical Bayesian parametric (BP) models can be used for health insurance claims forecasting, but they are unsatisfactory to describe the claims distribution. Therefore, Bayesian nonparametric (BNP) models can be a more suitable alternative to deal with the complex characteristics of the health insurance claims distribution, including heavy tails, skewness, and multimodality. In this study, we apply both a BP model and a BNP model to predict group health claims using simulated and real-world data for a private life insurer in Indonesia. The findings show that the BNP model outperforms the BP model in terms of claims prediction accuracy. Furthermore, our analysis highlights the flexibility and robustness of BNP models in handling diverse data structures in health insurance claims.

• Journal of the Korean Statistical Society
• /
• 제31권1호
• /
• pp.1-16
• /
• 2002

Since changepoint identification is important in many data analysis problem, we wish to make inference about the locations of one or more changepoints of the sequence. We consider the Bayesian nonparameteric inference for multiple changepoint problem using a Bayesian segmentation procedure proposed by Yang and Kuo (2000). A mixture of products of Dirichlet process is used as a prior distribution. To decide whether there exists a single change or not, our approach depends on nonparametric Bayesian Schwartz information criterion at each step. We discuss how to choose the precision parameter (total mass parameter) in nonparametric setting and show that the discreteness of the Dirichlet process prior can ha17e a large effect on the nonparametric Bayesian Schwartz information criterion and leads to conclusions that are very different results from reasonable parametric model. One example is proposed to show this effect.

• ETRI Journal
• /
• 제43권1호
• /
• pp.74-81
• /
• 2021

The mixture model is a very powerful and flexible tool in clustering analysis. Based on the Dirichlet process and parsimonious Gaussian distribution, we propose a new nonparametric mixture framework for solving challenging clustering problems. Meanwhile, the inference of the model depends on the efficient online variational Bayesian approach, which enhances the information exchange between the whole and the part to a certain extent and applies to scalable datasets. The experiments on the scene database indicate that the novel clustering framework, when combined with a convolutional neural network for feature extraction, has meaningful advantages over other models.

• Communications for Statistical Applications and Methods
• /
• 제29권3호
• /
• pp.287-299
• /
• 2022

In radiation epidemiology, the excess relative risk (ERR) model is used to determine the dose-response relationship. In general, the dose-response relationship for the ERR model is assumed to be linear, linear-quadratic, linear-threshold, quadratic, and so on. However, since none of these functions dominate other functions for expressing the dose-response relationship, a Bayesian semiparametric method using splines has recently been proposed. Thus, we improve the Bayesian semiparametric method for the selection of the tuning parameters for splines as the number and location of knots using a Bayesian knot selection method. Equally spaced knots cannot capture the characteristic of radiation exposed dose distribution which is highly skewed in general. Therefore, we propose a nonparametric Bayesian knot selection method based on a Dirichlet process mixture model. Inference of the spline coefficients after obtaining the number and location of knots is performed in the Bayesian framework. We apply this approach to the life span study cohort data from the radiation effects research foundation in Japan, and the results illustrate that the proposed method provides competitive curve estimates for the dose-response curve and relatively stable credible intervals for the curve.

• 한국데이터정보과학회:학술대회논문집
• /
• 한국데이터정보과학회 2005년도 춘계학술대회
• /
• pp.83-126
• /
• 2005

Single-index models have found applications in econometrics and biometrics, where multidimensional regression models are often encountered. Here we propose a nonparametric estimation approach that combines wavelet methods for non-equispaced designs with Bayesian models. We consider a wavelet series expansion of the unknown regression function and set prior distributions for the wavelet coefficients and the other model parameters. To ensure model identifiability, the direction parameter is represented via its polar coordinates. We employ ad hoc hierarchical mixture priors that perform shrinkage on wavelet coefficients and use Markov chain Monte Carlo methods for a posteriori inference. We investigate an independence-type Metropolis-Hastings algorithm to produce samples for the direction parameter. Our method leads to simultaneous estimates of the link function and of the index parameters. We present results on both simulated and real data, where we look at comparisons with other methods.

• 응용통계연구
• /
• 제27권6호
• /
• pp.1049-1068
• /
• 2014

자기회귀 모형(autoregressive model)은 일변량(univaraite) 시계열자료의 분석에서 널리 사용되는 방법 중 하나이다. 그러나 이 방법은 자료에 일정한 추세가 있다고 가정하기 때문에 자료에 분절(structural break)이 존재할 때 적절하지 않을 수 있다. 이러한 문제점을 해결하기 위한 방법으로 국면전환(regime-switching) 모형인 임계자기회귀 모형(threshold autoregressive model)이 제안되었는데 최근 지연 모수(delay parameter)을 포함한 이 국면전환(two regime-switching) 모형으로 확장되어 많은 연구가 활발히 진행되고 있다. 본 논문에서는 이 국면전환 임계자기회귀 모형을 베이지안(Bayesian) 관점에서 살펴본다. 베이지안 분석을 위해 모수적 임계자기 회귀 모형 뿐만 아니라 디리슐레 과정(Dirichlet Process) 사전분포를 이용하는 비모수적 임계자기 회귀 모형을 고려하도록 한다. 두 가지 베이지안 임계자기 회귀 모형을 바탕으로 사후분포를 유도하고 마코프 체인 몬테 카를로(Markov chain Monte Carlo) 방법을 통해 사후추론을 실시한다. 모형 간의 성능을 비교하기 위해 모의실험을 통한 자료 분석을 고려하고, 더 나아가 한국과 미국의 국내 총생산(Gross Domestic Product)에 대한 실증적 자료 분석을 실시한다.

• 약학회지
• /
• 제43권2호
• /
• pp.160-168
• /
• 1999

The purpose of this study was to determine pharmacokinetic parameters of vancomycin using peak and trough plasma level (PTL) and Bayesian analysis in 20 Korean normal volunteers, 16 gastric cancer and 12 lymphoma patients and also using the compartment model dependent (nonlinear least squares regression: NLSR) and compartment model independent (Lagrange) analysis in 10 ovarian cancer patients. Nonparametric expected maximum (NPEM) algorithm for calculation of the population pharmacokinetic parameters was used, and these parameters were applied for clinical pharmacokinetic parameters by Bayesian analysis. Vancomycin was administered as dose of 1.0 g every 12 hrs for 3 days by IV infusion over 60 minutes in normal volunteers, gastric cancer and lymphoma patients. Population pharmacokinetic parameters, K and Vd in gastric cancer and lymphoma patients using NPEM algorithm were $0.158{\pm}0.014{\;}hr^{-1},{\;}0.630{\pm}0.043{\;}L/kg{\;}and{\;}0.131{\pm}0.0261{\;}hr^{-1},{\;}0.631{\pm}0.089{\;}L/kg$ respectively. The K and Vd in gastric cancer and lymphoma patients using Bayesian analysis were $0.151{\pm}0.027,{\;}0.126{\pm}0.056{\;}hr^{-1}{\;}and{\;}0.62{\pm}0.105,{\;}0.63{\pm}0.095{\;}L/kg$. The K and Vd in ovarian cancer patient using the NLSR and Lagrange analysis were $0.109{\pm}0.008,{\;}0.126{\pm}0.012{\;}hr^{-1}{\;}and{\;} 0.76{\pm}0.08,{\;}0.69{\pm}0.19{\;}L/kg$, respectively. It is necessary for effective dosage regimen of vancomycin in cancer patients to use these population parameters.

• Journal of the Korean Statistical Society
• /
• 제31권4호
• /
• pp.509-518
• /
• 2002

This paper is concerned with semiparametric Bayesian analysis of the proportional intensity regression model of the Poisson process for multiple event time data. A nonparametric prior distribution is put on the baseline cumulative intensity function and a usual parametric prior distribution is given to the regression parameter. Also we allow heterogeneity among the intensity processes in different subjects by using unobserved random frailty components. Gibbs sampling approach with the Metropolis-Hastings algorithm is used to explore the posterior distributions. Finally, the results are applied to a real data set.

• 응용통계연구
• /
• 제29권4호
• /
• pp.627-641
• /
• 2016

본 논문에서는 겉보기 무관 회귀모형을 고려하고 디리크레 프로세스 혼합모형을 오차항의 분포로 하는 비모수 베이지안 방법을 제안한다. 제안된 모형을 바탕으로 사후분포를 유도하고 디리크레 프로세스 혼합모형의 붕괴깁스표집 방법을 통해 마코프 체인 몬테 칼로 알고리듬을 구성하고 사후추론을 실시한다. 모형의 성능을 비교하기 위해 모의실험을 실시하고, 더 나아가 한국지역의 강수량 예측에 대한 실제 자료에 적용해 본다.