Variable Selection for Nonparametric Gaussian Process Priors: Models and Computational Strategies

被引:59
|
作者
Savitsky, Terrance [1 ]
Vannucci, Marina [2 ]
Sha, Naijun [3 ]
机构
[1] RAND Corp, Santa Monica, CA 90401 USA
[2] Rice Univ, Dept Stat, Houston, TX 77030 USA
[3] Univ Texas El Paso, Dept Math Sci, El Paso, TX 79968 USA
基金
美国国家科学基金会;
关键词
Bayesian variable selection; generalized linear models; Gaussian processes; latent variables; MCMC; nonparametric regression; survival data; CHAIN MONTE-CARLO; BAYESIAN-ANALYSIS; REGRESSION; MIXTURES;
D O I
10.1214/11-STS354
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
This paper presents a unified treatment of Gaussian process models that extends to data from the exponential dispersion family and to survival data. Our specific interest is in the analysis of data sets with predictors that have an a priori unknown form of possibly nonlinear associations to the response. The modeling approach we describe incorporates Gaussian processes in a generalized linear model framework to obtain a class of nonparametric regression models where the covariance matrix depends on the predictors. We consider, in particular, continuous, categorical and count responses. We also look into models that account for survival outcomes. We explore alternative covariance formulations for the Gaussian process prior and demonstrate the flexibility of the construction. Next, we focus on the important problem of selecting variables from the set of possible predictors and describe a general framework that employs mixture priors. We compare alternative MCMC strategies for posterior inference and achieve a computationally efficient and practical approach. We demonstrate performances on simulated and benchmark data sets.
引用
收藏
页码:130 / 149
页数:20
相关论文
共 50 条
  • [1] Power-Expected-Posterior Priors for Variable Selection in Gaussian Linear Models
    Fouskakis, Dimitris
    Ntzoufras, Ioannis
    Draper, David
    [J]. BAYESIAN ANALYSIS, 2015, 10 (01): : 75 - 107
  • [2] Variable selection for Gaussian process models in computer experiments
    Linkletter, Crystal
    Bingham, Derek
    Hengartner, Nicholas
    Higdon, David
    [J]. TECHNOMETRICS, 2006, 48 (04) : 478 - 490
  • [3] Gibbs Priors for Bayesian Nonparametric Variable Selection with Weak Learners
    Linero, Antonio R.
    Du, Junliang
    [J]. JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS, 2023, 32 (03) : 1046 - 1059
  • [4] Spiked Dirichlet Process Priors for Gaussian Process Models
    Savitsky, Terrance
    Vannucci, Marina
    [J]. JOURNAL OF PROBABILITY AND STATISTICS, 2010, 2010
  • [5] VARIABLE SELECTION IN NONPARAMETRIC ADDITIVE MODELS
    Huang, Jian
    Horowitz, Joel L.
    Wei, Fengrong
    [J]. ANNALS OF STATISTICS, 2010, 38 (04): : 2282 - 2313
  • [6] Bayesian nonparametric quantile mixed-effects models via regularization using Gaussian process priors
    Tanabe, Yuta
    Araki, Yuko
    Kinoshita, Masahiro
    Okamura, Hisayoshi
    Iwata, Sachiko
    Iwata, Osuke
    [J]. JAPANESE JOURNAL OF STATISTICS AND DATA SCIENCE, 2022, 5 (01) : 241 - 267
  • [7] Bayesian nonparametric quantile mixed-effects models via regularization using Gaussian process priors
    Yuta Tanabe
    Yuko Araki
    Masahiro Kinoshita
    Hisayoshi Okamura
    Sachiko Iwata
    Osuke Iwata
    [J]. Japanese Journal of Statistics and Data Science, 2022, 5 : 241 - 267
  • [8] Flexible Link Functions in Nonparametric Binary Regression with Gaussian Process Priors
    Li, Dan
    Wang, Xia
    Lin, Lizhen
    Dey, Dipak K.
    [J]. BIOMETRICS, 2016, 72 (03) : 707 - 719
  • [9] Gaussian Latent Variable Models for Variable Selection
    Jiang, Xiubao
    You, Xinge
    Mou, Yi
    Yu, Shujian
    Zeng, Wu
    [J]. 2014 INTERNATIONAL CONFERENCE ON SECURITY, PATTERN ANALYSIS, AND CYBERNETICS (SPAC), 2014, : 353 - 357
  • [10] NONPARAMETRIC RANDOM EFFECTS FUNCTIONAL REGRESSION MODEL USING GAUSSIAN PROCESS PRIORS
    Wang, Zhanfeng
    Ding, Hao
    Chen, Zimu
    Shi, Jian Qing
    [J]. STATISTICA SINICA, 2021, 31 (01) : 53 - 78