Testing risk proxies for financial collateral haircuts: adequacy of capturing tail risk

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14560%2F20%3A00115950" target="_blank" >RIV/00216224:14560/20:00115950 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.emerald.com/insight/content/doi/10.1108/JRF-07-2019-0135/full/html" target="_blank" >https://www.emerald.com/insight/content/doi/10.1108/JRF-07-2019-0135/full/html</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1108/JRF-07-2019-0135" target="_blank" >10.1108/JRF-07-2019-0135</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Testing risk proxies for financial collateral haircuts: adequacy of capturing tail risk

Popis výsledku v původním jazyce

The use of risk proxies in internal models remains a popular modelling solution. However, there is some risk that a proxy may not constitute an adequate representation of the underlying asset in terms of capturing tail risk. Therefore, using empirical examples for the financial collateral haircut model, this paper aims to critically review available statistical tools for measuring the adequacy of capturing tail risk by proxies used in the internal risk models of banks. In doing so, this paper advises on the most appropriate solutions for validating risk proxies. This paper reviews statistical tools used to validate if the equity index/fund benchmark are proxies that adequately represent tail risk in the returns on an individual asset (equity/fund). The following statistical tools for comparing return distributions of the proxies and the portfolio items are discussed: the two-sample Kolmogorov–Smirnov test, the spillover test and the Harrell’s C test. Upon the empirical review of the available statistical tools, this paper suggests using the two-sample Kolmogorov–Smirnov test to validate the adequacy of capturing tail risk by the assigned proxy and the Harrell’s C test to capture the discriminatory power of the proxy-based collateral haircuts models. This paper also suggests a tool that compares the reactions of risk proxies to tail events to verify possible underestimation of risk in times of significant stress. The current regulations require banks to prove that the modelled proxies are representative of the real price observations without underestimation of tail risk and asset price volatility. This paper shows how to validate proxy-based financial collateral haircuts models.

Název v anglickém jazyce

Testing risk proxies for financial collateral haircuts: adequacy of capturing tail risk

Popis výsledku anglicky

The use of risk proxies in internal models remains a popular modelling solution. However, there is some risk that a proxy may not constitute an adequate representation of the underlying asset in terms of capturing tail risk. Therefore, using empirical examples for the financial collateral haircut model, this paper aims to critically review available statistical tools for measuring the adequacy of capturing tail risk by proxies used in the internal risk models of banks. In doing so, this paper advises on the most appropriate solutions for validating risk proxies. This paper reviews statistical tools used to validate if the equity index/fund benchmark are proxies that adequately represent tail risk in the returns on an individual asset (equity/fund). The following statistical tools for comparing return distributions of the proxies and the portfolio items are discussed: the two-sample Kolmogorov–Smirnov test, the spillover test and the Harrell’s C test. Upon the empirical review of the available statistical tools, this paper suggests using the two-sample Kolmogorov–Smirnov test to validate the adequacy of capturing tail risk by the assigned proxy and the Harrell’s C test to capture the discriminatory power of the proxy-based collateral haircuts models. This paper also suggests a tool that compares the reactions of risk proxies to tail events to verify possible underestimation of risk in times of significant stress. The current regulations require banks to prove that the modelled proxies are representative of the real price observations without underestimation of tail risk and asset price volatility. This paper shows how to validate proxy-based financial collateral haircuts models.

Druh

J_SC - Článek v periodiku v databázi SCOPUS

CEP obor

—

OECD FORD obor

50206 - Finance

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

The Journal of Risk Finance

ISSN

1526-5943

e-ISSN

—

Svazek periodika

21

Číslo periodika v rámci svazku

3

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

18

Strana od-do

299-316

Kód UT WoS článku

000547892100001

EID výsledku v databázi Scopus

2-s2.0-85087568428