{"title":"交互模型中省略的变量偏差:一个警示故事","authors":"B. Feigenberg, Ben Ost, Javaeria Qureshi","doi":"10.1162/rest_a_01361","DOIUrl":null,"url":null,"abstract":"\n We highlight that analyses using interaction terms to study treatment effect heterogeneity are susceptible to a form of omitted variable bias that is often overlooked in economics. Unlike most instances of omitted variable bias, the omitted variables in this case are available to the researcher but were not included in the model. We demonstrate that this exclusion matters based on a replication of 205 estimates across 17 papers published in the American Economic Review over a five-year period. For approximately 60% of these papers, failing to account for the omitted variables changes the majority of estimates by more than 100%.","PeriodicalId":48456,"journal":{"name":"Review of Economics and Statistics","volume":" ","pages":""},"PeriodicalIF":7.6000,"publicationDate":"2023-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Omitted Variable Bias in Interacted Models: A Cautionary Tale\",\"authors\":\"B. Feigenberg, Ben Ost, Javaeria Qureshi\",\"doi\":\"10.1162/rest_a_01361\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"\\n We highlight that analyses using interaction terms to study treatment effect heterogeneity are susceptible to a form of omitted variable bias that is often overlooked in economics. Unlike most instances of omitted variable bias, the omitted variables in this case are available to the researcher but were not included in the model. We demonstrate that this exclusion matters based on a replication of 205 estimates across 17 papers published in the American Economic Review over a five-year period. For approximately 60% of these papers, failing to account for the omitted variables changes the majority of estimates by more than 100%.\",\"PeriodicalId\":48456,\"journal\":{\"name\":\"Review of Economics and Statistics\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":7.6000,\"publicationDate\":\"2023-07-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Review of Economics and Statistics\",\"FirstCategoryId\":\"96\",\"ListUrlMain\":\"https://doi.org/10.1162/rest_a_01361\",\"RegionNum\":1,\"RegionCategory\":\"经济学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ECONOMICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Review of Economics and Statistics","FirstCategoryId":"96","ListUrlMain":"https://doi.org/10.1162/rest_a_01361","RegionNum":1,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ECONOMICS","Score":null,"Total":0}
Omitted Variable Bias in Interacted Models: A Cautionary Tale
We highlight that analyses using interaction terms to study treatment effect heterogeneity are susceptible to a form of omitted variable bias that is often overlooked in economics. Unlike most instances of omitted variable bias, the omitted variables in this case are available to the researcher but were not included in the model. We demonstrate that this exclusion matters based on a replication of 205 estimates across 17 papers published in the American Economic Review over a five-year period. For approximately 60% of these papers, failing to account for the omitted variables changes the majority of estimates by more than 100%.
期刊介绍:
The Review of Economics and Statistics is a 100-year-old general journal of applied (especially quantitative) economics. Edited at the Harvard Kennedy School, the Review has published some of the most important articles in empirical economics.