有限样本量下安德森-达令检验的效率:应用于交易对手信用风险内部模型的回测

IF 0.3 4区经济学 Q4 BUSINESS, FINANCE

Journal of Risk Pub Date : 2019-01-01 DOI:10.21314/jor.2019.415

Matteo Formenti, Luca Spadafora, Marcello Terraneo, Fabio Ramponi

{"title":"有限样本量下安德森-达令检验的效率:应用于交易对手信用风险内部模型的回测","authors":"Matteo Formenti, Luca Spadafora, Marcello Terraneo, Fabio Ramponi","doi":"10.21314/jor.2019.415","DOIUrl":null,"url":null,"abstract":"This work presents a theoretical and empirical evaluation of the Anderson–Darling test when the sample size is limited. The test can be used to backtest risk factor dynamics in the context of counterparty credit risk modeling. We show the limits of the test when backtesting the distributions of an interest rate model over long time horizons, and we propose a modified version of it that can more efficiently detect the underestimation of a model’s volatility. Finally, we provide an empirical application.","PeriodicalId":46697,"journal":{"name":"Journal of Risk","volume":"6 23","pages":""},"PeriodicalIF":0.3000,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"The efficiency of the Anderson–Darling test with a limited sample size: an application to backtesting counterparty credit risk internal models\",\"authors\":\"Matteo Formenti, Luca Spadafora, Marcello Terraneo, Fabio Ramponi\",\"doi\":\"10.21314/jor.2019.415\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This work presents a theoretical and empirical evaluation of the Anderson–Darling test when the sample size is limited. The test can be used to backtest risk factor dynamics in the context of counterparty credit risk modeling. We show the limits of the test when backtesting the distributions of an interest rate model over long time horizons, and we propose a modified version of it that can more efficiently detect the underestimation of a model’s volatility. Finally, we provide an empirical application.\",\"PeriodicalId\":46697,\"journal\":{\"name\":\"Journal of Risk\",\"volume\":\"6 23\",\"pages\":\"\"},\"PeriodicalIF\":0.3000,\"publicationDate\":\"2019-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Risk\",\"FirstCategoryId\":\"96\",\"ListUrlMain\":\"https://doi.org/10.21314/jor.2019.415\",\"RegionNum\":4,\"RegionCategory\":\"经济学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"BUSINESS, FINANCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Risk","FirstCategoryId":"96","ListUrlMain":"https://doi.org/10.21314/jor.2019.415","RegionNum":4,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"BUSINESS, FINANCE","Score":null,"Total":0}

引用次数: 0

摘要

这项工作提出了安德森-达令测试的理论和实证评价时，样本量有限。该测试可用于对交易对手信用风险建模背景下的风险因素动态进行回测。我们在对长期利率模型的分布进行回溯测试时显示了该测试的局限性，并提出了一个改进版本，可以更有效地检测模型波动性的低估。最后，我们提供了一个实证应用。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

The efficiency of the Anderson–Darling test with a limited sample size: an application to backtesting counterparty credit risk internal models

This work presents a theoretical and empirical evaluation of the Anderson–Darling test when the sample size is limited. The test can be used to backtest risk factor dynamics in the context of counterparty credit risk modeling. We show the limits of the test when backtesting the distributions of an interest rate model over long time horizons, and we propose a modified version of it that can more efficiently detect the underestimation of a model’s volatility. Finally, we provide an empirical application.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Journal of Risk BUSINESS, FINANCE-

CiteScore

1.00

自引率

14.30%

发文量

期刊介绍： This international peer-reviewed journal publishes a broad range of original research papers which aim to further develop understanding of financial risk management. As the only publication devoted exclusively to theoretical and empirical studies in financial risk management, The Journal of Risk promotes far-reaching research on the latest innovations in this field, with particular focus on the measurement, management and analysis of financial risk. The Journal of Risk is particularly interested in papers on the following topics: Risk management regulations and their implications, Risk capital allocation and risk budgeting, Efficient evaluation of risk measures under increasingly complex and realistic model assumptions, Impact of risk measurement on portfolio allocation, Theoretical development of alternative risk measures, Hedging (linear and non-linear) under alternative risk measures, Financial market model risk, Estimation of volatility and unanticipated jumps, Capital allocation.