Geometric Sensitivity Measures for Bayesian Nonparametric Density Estimation Models

被引:0
|
作者
Saha, Abhijoy [1 ]
Kurtek, Sebastian [1 ]
机构
[1] Ohio State Univ, Dept Stat, Columbus, OH 43210 USA
关键词
Global sensitivity analysis; Fisher-Rao metric; Bayesian nonparametric density estimation; square-root density; Dirichlet process; Dirichlet process Gaussian mixture model; Primary; Secondary; LOCAL SENSITIVITY; SAMPLING METHODS; UNKNOWN NUMBER; MIXTURE-MODELS; DISTRIBUTIONS; INFERENCE;
D O I
10.1007/s13171-018-0145-7
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
We propose a geometric framework to assess global sensitivity in Bayesian nonparametric models for density estimation. We study sensitivity of nonparametric Bayesian models for density estimation, based on Dirichlet-type priors, to perturbations of either the precision parameter or the base probability measure. To quantify the different effects of the perturbations of the parameters and hyperparameters in these models on the posterior, we define three geometrically-motivated global sensitivity measures based on geodesic paths and distances computed under the nonparametric Fisher-Rao Riemannian metric on the space of densities, applied to posterior samples of densities: (1) the Fisher-Rao distance between density averages of posterior samples, (2) the log-ratio of Karcher variances of posterior samples, and (3) the norm of the difference of scaled cumulative eigenvalues of empirical covariance operators obtained from posterior samples. We validate our approach using multiple simulation studies, and consider the problem of sensitivity analysis for Bayesian density estimation models in the context of three real datasets that have previously been studied.
引用
收藏
页码:104 / 143
页数:40
相关论文
共 50 条
  • [1] Geometric Sensitivity Measures for Bayesian Nonparametric Density Estimation Models
    Abhijoy Saha
    Sebastian Kurtek
    [J]. Sankhya A, 2019, 81 (1): : 104 - 143
  • [2] Nonparametric estimation of probabilistic sensitivity measures
    Antoniano-Villalobos, Isadora
    Borgonovo, Emanuele
    Lu, Xuefei
    [J]. STATISTICS AND COMPUTING, 2020, 30 (02) : 447 - 467
  • [3] Nonparametric estimation of probabilistic sensitivity measures
    Isadora Antoniano-Villalobos
    Emanuele Borgonovo
    Xuefei Lu
    [J]. Statistics and Computing, 2020, 30 : 447 - 467
  • [4] A SENSITIVITY ANALYSIS FOR BAYESIAN NONPARAMETRIC DENSITY ESTIMATORS
    Nieto-Barajas, Luis E.
    Prunster, Igor
    [J]. STATISTICA SINICA, 2009, 19 (02) : 685 - 705
  • [5] Bayesian Nonparametric Spatially Smoothed Density Estimation
    Hanson, Timothy
    Zhou, Haiming
    de Carvalho, Vanda Inacio
    [J]. NEW FRONTIERS OF BIOSTATISTICS AND BIOINFORMATICS, 2018, : 87 - 105
  • [6] Comparison of Bayesian nonparametric density estimation methods
    Bedoui, Adel
    Rosen, Ori
    [J]. COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, 2022, 51 (19) : 6667 - 6682
  • [7] SOME ASPECTS OF BAYESIAN NONPARAMETRIC INFERENCE UNDER DENSITY ESTIMATION, REGRESSION AND SURVIVAL MODELS
    Kumar, Shailendra
    Pandey, Anshula
    Sehgal, V. K.
    [J]. INTERNATIONAL JOURNAL OF AGRICULTURAL AND STATISTICAL SCIENCES, 2018, 14 (02): : 627 - 635
  • [8] Bayesian nonparametric density estimation under length bias
    Hatjispyros, Spyridon J.
    Nicoleris, Theodoros
    Walker, Stephen G.
    [J]. COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION, 2017, 46 (10) : 8064 - 8076
  • [9] On consistency of nonparametric normal mixtures for Bayesian density estimation
    Lijoi, A
    Prünster, I
    Walker, SG
    [J]. JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2005, 100 (472) : 1292 - 1296
  • [10] Bayesian field theory nonparametric approaches to density estimation
    Lemm, JC
    [J]. IJCNN 2000: PROCEEDINGS OF THE IEEE-INNS-ENNS INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOL II, 2000, : 18 - 22