Macro Stress Testing with a Macroeconomic Credit Risk Model for Finland

Abstract

In the discussion paper, we employ data on industry-specific corporate sector bankruptcies over the time period from 1986 to 2003 and estimate a macroeconomic credit risk model for the Finnish corporate sector. The sample period includes a severe recession with significantly higher-than-average default rates in the early 1990s. The results suggest a significant relationship between corporate sector default rates and key macroeconomic factors including GDP, interest rates and corporate indebtedness. The estimated model is employed to analyse corporate credit risks conditional on current macroeconomic conditions. Furthermore, the paper presents some examples of applying the model to macro stress testing, ie analysing the effects of various adverse macroeconomic events on the banks' credit risks stemming from the corporate sector. The results of the stress tests suggest that Finnish corporate sector credit risks are fairly limited in the current macroeconomic environment.

Stress testing credit card portfolios: an application in South Africa

“…It is common for GDP to be picked up as a key macroeconomic variable in credit risk analysis (e.g. Altman et al, 2001;Virolainen, 2004 White's Test (White, 1980) was used to test for heteroscedasticity of the residuals. This was to ensure homogeneity of variance of residuals, which is an assumption when Ordinary Least Squares Regression is carried out.…”

“…The first was a regression based model with autocorrelation errors. These models are the main approach to stress testing credit portfolios (Jiménez and Mencía, 2009;Wong et al, 2006;Virolainen, 2004). In these models, default rate is the dependent variable and macroeconomic variable(s) (e.g.…”

Stress Testing of Commercial Banks’ Exposure to Credit Risk: A Study Based on Write-off Nonperforming Loans

“…This paper develops macro stress-test models by Wilson (1997aWilson ( ,1997b, Boss (2002) and Virolainen (2004) and creates a new conceptual model that could be applied to Chinese commercial banks. Our framework consists of two parts: one part refers to empirical model concerning credit risk of commercial bank as well as macro economical system.…”

Dynamic Factor Analysis of Industry Sector Default Rates and Implication for Portfolio Credit Risk Modelling

“…White noise Gaussian random draws are the realisations of the unobservable common shock and they allow to build the density forecast of default rates. The study of the Portfolio Loss density forecast in Virolainen (2004) is based upon the SUR estimation of a system of equations explaining logit transformed industry sector default rates for the Finnish economy through common observable factors. These are macro time series and they are modelled through an AR(2) process.…”

“…cit. ) method has the flavour of a structural form Portfolio Credit Risk model, the studies of Hamerle et al (2004) and Virolainen (2004) are reduced form models in which the simulation the bank loan Portfolio Loss density is obtained after estimating the impact of key macro variables on industry sector default rates. Given that we observe historical industry sector default rates, in our study we concentrate on a reduced form modelling for the purpose of Portfolio Credit Risk analysis similar to the studies of Credit Portfolio View (see Wilson, 1997), of Virolainen (2004) and of Hamerle et al (2004).…”