{"title":"A Practical Method for Sharpening Estimates of Industry Equity Capital Costs","authors":"Mike Aguilar, Robert A. Connolly, Jiaxia Li","doi":"10.2139/ssrn.3742221","DOIUrl":null,"url":null,"abstract":"We propose a method for reducing standard errors associated with industry equity capital costs (ECC), a problem studied by Fama French (1997). Approximately 90% of the uncertainty regarding ECC estimates comes from the factor risk premia, as opposed to factor exposures. Furthermore, at least 75% of the uncertainty regarding these risk premia is driven by the standard error of the second pass regression. These standard errors are inflated by seasonal noise in the return process. By filtering this noise, we generate ECC estimates that are unchanged on average, but with standard errors that are about one-quarter of the size without filtering.","PeriodicalId":11410,"journal":{"name":"Econometric Modeling: Capital Markets - Risk eJournal","volume":"21 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2020-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Econometric Modeling: Capital Markets - Risk eJournal","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2139/ssrn.3742221","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
We propose a method for reducing standard errors associated with industry equity capital costs (ECC), a problem studied by Fama French (1997). Approximately 90% of the uncertainty regarding ECC estimates comes from the factor risk premia, as opposed to factor exposures. Furthermore, at least 75% of the uncertainty regarding these risk premia is driven by the standard error of the second pass regression. These standard errors are inflated by seasonal noise in the return process. By filtering this noise, we generate ECC estimates that are unchanged on average, but with standard errors that are about one-quarter of the size without filtering.