• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to project page

2020 Fiscal Year Final Research Report

Bayesian analysis of cause of death assignment using verbal autopsy data

Research Project

  • PDF
Project/Area Number 18K12756
Research Category

Grant-in-Aid for Early-Career Scientists

Allocation TypeMulti-year Fund
Review Section Basic Section 07030:Economic statistics-related
Research InstitutionKwansei Gakuin University

Principal Investigator

KUNIHAMA Tsuyoshi  関西学院大学, 経済学部, 准教授 (40779716)

Project Period (FY) 2018-04-01 – 2021-03-31
Keywordsベイズ統計学 / マルコフ連鎖モンテカルロ法
Outline of Final Research Achievements

This research develops a new statistical method for prediction of causes of death with verbal autopsy data, taking into account characteristics of surveys about health history and symptoms of the deceased. The proposed statistical model relies on less assumptions than existing methods, by incorporating count, categorical, continuous variables as well as binary ones in the framework. Moreover, for the proposed method, a new algorithm is developed for prediction of causes of death using real survey data.

Free Research Field

経済統計

Academic Significance and Societal Importance of the Research Achievements

提案手法は口頭剖検のための統計手法として,既存のアプローチに比べて聞き取り調査データの特徴を柔軟に捉えることができるため,発展途上国の死因分布の推定精度の向上や既存分析の妥当性の検証のために役立つと考える.加えて,一般の多変量データ解析のための統計手法としても,提案手法は複雑な相関構造や様々な観測尺度を有する高次元データの分析を目的とするため,部分的に他分野への応用も可能である.例えば,多くの社会調査は多数の質問項目から構成され,項目間の複雑な関係性,頻出する欠損値の存在,異なる観測尺度など,本研究で取り組んだデータの特徴との類似点があると考えられる.

URL: 

Published: 2022-01-27  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi