{"title":"Addressing Probationary Period within a Competing Risks Survival Model for Retail Mortgage Loss Given Default","authors":"R. Wood, David Powell","doi":"10.21314/JCR.2017.228","DOIUrl":null,"url":null,"abstract":"This paper builds on the established two-stage modeling framework for retail mortgages in which loss given default is computed as the product of property possession given default probability and loss given possession. In deriving the former, previous studies have suffered from a lack of clarity in their definitions of the post default outcomes of “cure” (no loss) and “possession” (some loss). The present study remedies this through the use of competing risks survival analysis, where to cure requires completion of a probationary period in which accounts return to nondefault status only when the ability to make repayments is demonstrated for a certain number of consecutive months (a recent regulatory requirement of the European Banking Authority). For loss given possession the distribution of survival time until this event can be conveniently used to appreciate the discounting of future receivables from property sale.","PeriodicalId":203996,"journal":{"name":"ERN: Value-at-Risk (Topic)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ERN: Value-at-Risk (Topic)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.21314/JCR.2017.228","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
This paper builds on the established two-stage modeling framework for retail mortgages in which loss given default is computed as the product of property possession given default probability and loss given possession. In deriving the former, previous studies have suffered from a lack of clarity in their definitions of the post default outcomes of “cure” (no loss) and “possession” (some loss). The present study remedies this through the use of competing risks survival analysis, where to cure requires completion of a probationary period in which accounts return to nondefault status only when the ability to make repayments is demonstrated for a certain number of consecutive months (a recent regulatory requirement of the European Banking Authority). For loss given possession the distribution of survival time until this event can be conveniently used to appreciate the discounting of future receivables from property sale.