{"title":"对IHME Covid-19模型的评估:2020年美国死亡人数","authors":"T. R. Robbins","doi":"10.33423/ajm.v21i2.4225","DOIUrl":null,"url":null,"abstract":"The Covid-19 forecasting model published by the Institute for Health Metrics and Evaluation (IHME) is one of the most influential, consequential, and controversial forecasting models ever published. The model has been widely cited by policy makers, but it has also been widely criticized. In this paper we make an objective, external review of the model. We evaluate the outputs of the model, how they changed, and how they compared to actual results. The model was subject to frequent adjustment that resulted in wide swings back and forth. The errors associated with the model were high and actual results fell inside the model's reported 95% confidence interval far less than 95% of the time. Overall, we find the accuracy of the model was poor, and the model 's predictions were unrealistically precise.","PeriodicalId":91998,"journal":{"name":"American journal of information management","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2021-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"An Assessment of the IHME Covid-19 Model: US Fatalities in 2020\",\"authors\":\"T. R. Robbins\",\"doi\":\"10.33423/ajm.v21i2.4225\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The Covid-19 forecasting model published by the Institute for Health Metrics and Evaluation (IHME) is one of the most influential, consequential, and controversial forecasting models ever published. The model has been widely cited by policy makers, but it has also been widely criticized. In this paper we make an objective, external review of the model. We evaluate the outputs of the model, how they changed, and how they compared to actual results. The model was subject to frequent adjustment that resulted in wide swings back and forth. The errors associated with the model were high and actual results fell inside the model's reported 95% confidence interval far less than 95% of the time. Overall, we find the accuracy of the model was poor, and the model 's predictions were unrealistically precise.\",\"PeriodicalId\":91998,\"journal\":{\"name\":\"American journal of information management\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-06-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"American journal of information management\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.33423/ajm.v21i2.4225\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"American journal of information management","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.33423/ajm.v21i2.4225","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
An Assessment of the IHME Covid-19 Model: US Fatalities in 2020
The Covid-19 forecasting model published by the Institute for Health Metrics and Evaluation (IHME) is one of the most influential, consequential, and controversial forecasting models ever published. The model has been widely cited by policy makers, but it has also been widely criticized. In this paper we make an objective, external review of the model. We evaluate the outputs of the model, how they changed, and how they compared to actual results. The model was subject to frequent adjustment that resulted in wide swings back and forth. The errors associated with the model were high and actual results fell inside the model's reported 95% confidence interval far less than 95% of the time. Overall, we find the accuracy of the model was poor, and the model 's predictions were unrealistically precise.