COVID-19のオープンデータを用いた時系列解析による政策等の影響分析と教育化

通过使用有关 COVID-19 的开放数据的时间序列分析，对政策等的影响进行分析和教育

• 批准号: 22K11946
• 负责人: 濱田 悦生
• 金额: $ 1.08万
• 依托单位: Osaka Institute of Technology
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (C)
• 财政年份: 2022
• 资助国家: 日本
• 起止时间: 2022-04-01 至 2025-03-31
• 项目状态: 未结题
• 来源: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-22K11946/
• 关键词: COVID-19; SARIMAモデル; VARモデル; Granger因果性; オープンデータ; 時系列解析; 影響分析; 教育化

厚生労働省による COVID-19 のオープンデータを用いた時系列解析を実施することにより, PCR 陽性者数や感染死亡者数等に関する時系列データから, 如何にそれらの関連性や因果性があるかを時系列モデルを基に解析することが研究の概要である。令和4年度の研究計画としては、令和 2年１月から令和 4年 3月までのオープンデータに対して,1. PCR 陽性者数データのスクリーニング、2. ウイルスの変異傾向における時系列 (SARIMA) モデルの推定、3. PCR 陽性者数, 重症者数と感染死亡者数との VAR モデルにおける Granger 因果性の推定、を様々な解析期間（1 か月間, 2 か月間, 3 か月間など）において都道府県別及び全国集計から実験計画的な手法を用いて分析することを予定していた。都道府県別データでのスクリーニングを実行してみると、オープンデータの感染死亡者数において、茨城県・兵庫県・熊本県に不備や問題があることが判明した。令和2年5月9日から令和5年3月31日までの感染死亡者数のSARIMAモデルによる分析結果としては、SARIMA(2,2,3)x(1,0,1)[7] モデルが多く選ばれ、2階差分がどの都道府県でも推定された。令和2年1月6日から令和5年3月31日までのPCR陽性者数のSARIMAモデルによる分析結果は、ほぼどの都道府県も同じような結果となり、SARIMA(2,0,3)x(1,1,1)[7] モデルが多数であった。VARモデルにおけるPCR陽性者数と感染死亡者数における Granger 因果性における分散分解では、1次差分を行い VAR(15) モデルを推定し、感染死亡者数に対するPCR陽性者数の90日後の影響割合が20%であった。

The health care system is responsible for the analysis of the time series, such as the number of people who have sex with COVID-19, the number of people who have sex with PCR, the number of people who have died of infection, and the number of people who have died of infection, and so on, and how to analyze the relationship between sex and causality. The summary of the study. Ling and 4 years of research projects, orders and orders in January of 2 years and 3 months of 4 years, 1. The number of people who have sex in PCR, the number of people who have sex, 2. The number of people suffering from PCR infection, the number of severe cases, the number of deaths caused by infection, the presumption of causality, the period of analysis (within 1 month, 2 months), the presumption of causality and the period of analysis. (3) during the month, the government and the national collection of statistics were used to analyze and predict the design of the city. The prefecture did not pay any attention to the number of people who died of infection, the number of people who died of infection, and the number of people who died of infection. The results of the analysis of the number of people who died of SARIMA infection on May 9, 2002 and March 31, 2005 were analyzed. The results showed that the number of people who died of infection was estimated to be infected by SARIMA (2pc2) x (1p0) x (1p0l1) [7], and 2% of the total number of people who died of infection. On January 6, 2000 and March 31, 2005, the number of people who had sex with SARIMA was analyzed. The results showed that most of them were found to have sex with each other. The results showed that the number of people who had sex with each other on January 6, 2002 and March 31, 2005 were analyzed. The results showed that most of them were infected. The number of people who died of VAR infection, the number of people who died of PCR, the number of people who died of infection, the number of people who died of PCR, the number of people who died of infection, the number of people who died of infection, the number of people who died of PCR, the number of people who died of infection, the