arXiv subjects

Guanyu Hu

Publications and source records attributed to Guanyu Hu.

59 records · Page 4Linked to original sources

arXiv2020

A comparison of Bayesian accelerated failure time models with spatially varying coefficients

The accelerated failure time (AFT) model is a commonly used tool in analyzing survival data. In public health studies, data is often collected from medical service providers in different locations. Survival rates from different locations often present geographically varying patterns. In this paper, we focus on the accelerated failure time model with spatially varying coefficients. We compare three types of the priors for spatially varying coefficients. A model selection criterion, logarithm of the pseudo-marginal likelihood (LPML), is developed to assess the fit of AFT model with different priors. Extensive simulation studies are carried out to examine the empirical performance of the proposed methods. Finally, we apply our model to SEER data on prostate cancer in Louisiana and demonstrate the existence of spatially varying effects on survival rates from prostate cancer data.

stat.AP↗

arXiv2019

Spatial Weibull Regression with Multivariate Log Gamma Process and Its Applications to China Earthquake Economic Loss

Bayesian spatial modeling of heavy-tailed distributions has become increasingly popular in various areas of science in recent decades. We propose a Weibull regression model with spatial random effects for analyzing extreme economic loss. Model estimation is facilitated by a computationally efficient Bayesian sampling algorithm utilizing the multivariate Log-Gamma distribution. Simulation studies are carried out to demonstrate better empirical performances of the proposed model than the generalized linear mixed effects model. An earthquake data obtained from Yunnan Seismological Bureau, China is analyzed. Logarithm of the Pseudo-marginal likelihood values are obtained to select the optimal model, and Value-at-risk, expected shortfall, and tail-value-at-risk based on posterior predictive distribution of the optimal model are calculated under different confidence levels.

stat.AP↗

arXiv2019

New Development of Bayesian Variable Selection Criteria for Spatial Point Process with Applications

Selecting important spatial-dependent variables under the nonhomogeneous spatial Poisson process model is an important topic of great current interest. In this paper, we use the Deviance Information Criterion (DIC) and Logarithm of the Pseudo Marginal Likelihood (LPML) for Bayesian variable selection under the nonhomogeneous spatial Poisson process model. We further derive the new Monte Carlo estimation formula for LPML in the spatial Poisson process setting. Extensive simulation studies are carried out to evaluate the empirical performance of the proposed criteria. The proposed methodology is further applied to the analysis of two large data sets, the Earthquake Hazards Program of United States Geological Survey (USGS) earthquake data and the Forest of Barro Colorado Island (BCI) data.

stat.AP↗

arXiv2019

Geographically Weighted Cox Regression for Prostate Cancer Survival Data in Louisiana

The Cox proportional hazard model is one of the most popular tools in analyzing time-to-event data in public health studies. When outcomes observed in clinical data from different regions yield a varying pattern correlated with location, it is often of great interest to investigate spatially varying effects of covariates. In this paper, we propose a geographically weighted Cox regression model for sparse spatial survival data. In addition, a stochastic neighborhood weighting scheme is introduced at the county level. Theoretical properties of the proposed geographically weighted estimators are examined in detail. A model selection scheme based on the Takeuchi's model robust information criteria (TIC) is discussed. Extensive simulation studies are carried out to examine the empirical performance of the proposed methods. We further apply the proposed methodology to analyze real data on prostate cancer from the Surveillance, Epidemiology, and End Results cancer registry for the state of Louisiana.

stat.AP↗

arXiv2019

Bayesian Nonparametric Nonhomogeneous Poisson Process with Applications to USGS Earthquake Data

Intensity estimation is a common problem in statistical analysis of spatial point pattern data. This paper proposes a nonparametric Bayesian method for estimating the spatial point process intensity based on mixture of finite mixture (MFM) model. MFM approach leads to a consistent estimate of the intensity of spatial point patterns in different areas while considering heterogeneity. An efficient Markov chain Monte Carlo (MCMC) algorithm is proposed for our method. Extensive simulation studies are carried out to examine empirical performance of the proposed method. The usage of our proposed method is further illustrated with the analysis of the Earthquake Hazards Program of United States Geological Survey (USGS) earthquake data.

stat.ME↗