search for




 

Radiation response data analysis using Bayesian nonparametric regression models with shape-restriction†
Journal of the Korean Data & Information Science Society 2021;32:1295-304
Published online November 30, 2021;  https://doi.org/10.7465/jkdi.2021.32.6.1295
© 2021 Korean Data and Information Science Society.

Seongil Jo1 · Seungwon Seo2 · Kwangwoo Jung3 · Hyoungwoo Bai4

1Department of Statistics, Inha University
2Insilcogen
34Radiation Research Division, Advanced Radiation Technology Institute, Korea Atomic Energy Research Institute
Correspondence to: 1 Associate professor, Department of Statistics, Inha University, Incheon 22212, Korea.
2 Insilicogen, Gyeonggi-do 16954, Korea.
3 Radiation Research Division, Advanced Radiation Technology Institute, Korea Atomic Energy Research Institute, Jeongeup-si 56212, Jeollabuk-do, Korea
4 Corresponding author, Radiation Research Division, Advanced Radiation Technology Institute, Korea Atomic Energy Research Institute, Jeongeup-si 56212, Jeollabuk-do, Korea. E-mail: hbai@kaeri.re.kr
Research of Seongil Jo was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (NRF-2020R1C1C1A01013338).
Received September 10, 2021; Revised October 1, 2021; Accepted October 5, 2021.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
In this paper we analyze radiation response data using Bayesian nonparametric regression models with shape-restriction. Particularly, we present a Bayesian inference for analysis of radiation response data obtained by irradiating polymer material and food with radiation. For Bayesian inference, we approximate a posterior distribution using a Gaussian variational Bayes algorithm that uses Gaussian distributions as variational approximation distributions. We compare the variational approximation algorithm with a Markov chain Monte Carlo method that is based on Hamiltonian Monte Carlo and then present validity of variational inference.
Keywords : Automatic differentiation variatioonal inference, Bayesian inference, radiation response data, shape-restricted nonparametric regression models, variational inference.