Abstract
We propose factor-based out-of-sample forecast models for Korea’s financial stress index and its 4 subindices that are developed by the Bank of Korea. We extract latent common factors by employing the method of the principal components for a panel of 198 monthly frequency macroeconomic data after differencing them. We augment an autoregressive-type model of the financial stress index with estimated common factors to formulate out-of-sample forecasts of the index. Our models overall outperform both the stationary and the nonstationary benchmark models in forecasting the financial stress indices for up to 12-month forecast horizons. The first common factor that represents not only financial market but also real activity variables seems to play a dominantly important role in predicting the vulnerability in the financial markets in Korea.
Similar content being viewed by others
Notes
Source: Organization for Economic Co-operation and Development, Total Share Prices for All Shares for the Republic of Korea [SPASTT01KRQ657N].
For some of FSIs in the Euro, see Grimaldi (2010), Grimaldi (2011), Hollo et al. (2012), and Islami et al. (2013). There are FSIs for individual countries: Greece (Louzis and Vouldis 2011), Sweden (Sandahl et al. 2011), Canada (Illing and Liu 2006), Denmark (Hansen 2006), Switzerland (Hanschel and Monnin 2005), Germany (van Roye 2011), Turkey (Cevik et al. 2013), Colombia (Morales and Estrada 2010), and Hong Kong (Yiu et al. 2010).
The 4 subindices are for the foreign exchange market, the stock market, the bond market, and the financial industry in Korea.
The data are not publicly available and are for internal use only. We express our gratitude to give permission to use the data.
We categorized these 198 variables into 13 groups that include an array of nominal and real activity variables.
Principal component may not be ideal under certain circumstances. For example, Brave and Butters (2011) point out that this approach can have limitations when data are available at different data frequencies. On the other hand, the maximum likelihood and Kalman filter deal with the missing values and the varying frequency data observation. That is, weekly, monthly, and quarterly data with histories that potentially begin and end at different points of time could be used. We collected macroeconomic data up to 198 variables on the monthly basis without missing observations to match the frequency of the Bank of Korea’s FSI. Therefore, we believe PCA is a legitimate and appropriate approach for our purpose.
Alternatively, one may use a recursive forecasting regression model that replaces \(\alpha _{j}\) with \(\alpha ^{j}\), where \(\alpha \) is the coefficient from an AR(1) model.
ADF test results are available upon request.
Following Andrews and Monahan (1992), we use the quadratic spectral kernel with automatic bandwidth selection for our analysis.
We obtained permission from the Bank of Korea to use the data for this research.
Regressions for the 1-, 3-, and 6-month ahead FSI indices yield similar patterns, although \(R^{2}\) values overall decline as the time horizon becomes larger.
We used 70% initial observations.
Note that some variables such as Korean stock indices and bilateral exchange rates were included in our baseline study.
Alternative interpretation would be that our finding is consistent with a view that Korean policy makers were able to isolate domestic financial market conditions from external shocks. See Arregui et al. (2018) for detailed discussions on this issue.
Duprey (2018) provides similar Canadian evidence.
In a closely related paper, De Nicolò and Lucchetta (2017) demonstrate that quantile projection models have provided more accurate and reliable early warning signals than AR and factor augmented VAR models for tail real and financial risks in the USA up to a 1-year forecast horizon.
For example in the USA, the Federal Reserve Bank of Cleveland interprets the Z-score Cleveland Financial Stress Index (CFSI) by dividing it into four levels or grades: Grade 1 Low stress period \(CFSI<-\,0.733\); Grade 2 Normal stress period \(-\,0.733\ge \hbox {CFSI}<0.544\); Grade 3 Moderate stress period \(0.544\ge \hbox {CFSI}<1.82\); and Grade 4 Significant stress period \(\hbox {CFSI}\ge 1.82\).
We also implemented quantile analyses with two common factor estimates that performed similarly well.
References
Adrian T, Boyarchenko N, Giannone D (2016) Vulnerable growth. Staff Reports 794, Federal Reserve Bank of New York
Adrian T, Grinberg F, Liang N, Malik S (2018) The term structure of growth-at-risk. IMF Working Papers 18/180, International Monetary Fund
Andrews DWK, Monahan JC (1992) An improved heteroskedasticity and autocorrelation consistent covariance matrix estimator. Econometrica 60(4):953–966
Arregui N, Elekdag S, Gelos G, Lafarguette R, Seneviratne D (2018) Can countries manage their financial conditions amid globalization. IMF Working Paper 18/15. International Monetary Fund
Bai J, Ng S (2004) A panic attack on unit roots and cointegration. Econometrica 72:1127–1177
Berg A, Pattillo C (1999) Predicting currency crises: the indicators approach and an alternative. J Int Money Finance 18(4):561–586
Berg A, Borensztein E, Pattillo C (2005) Assessing early warning systems: How have they worked in practice? IMF Working Paper 04/52. International Monetary Fund
Brave S, Butters RA (2011) Monitoring financial stability: a financial conditions index approach. Econ Perspect 35:22–43
Brüggemann A, Linne T (1999) How good are leading indicators for currency and banking crises in Central and Eastern Europe? An empirical test. IWH Discussion Papers, 95. Halle Institute for Economic Research
Bussiere M, Mulder C (1999) External vulnerability in emerging market economies—how high liquidity can offset weak fundamentals and the effects of contagion. IMF Working Papers 99/88
Cevik EI, Diboogu S, Kenc T (2013) Measuring financial stress in Turkey. J Policy Model 35:370–383
Christensen I, Li F (2014) Predicting financial stress events: a signal extraction approach. Working Paper 2014-37. Bank of Canada
Cipollini A, Kapetanios G (2009) Forecasting financial crises and contagion in Asia using dynamic factor analysis. J Empir Finance 16(2):188–200
De Nicolò G, Lucchetta M (2017) Forecasting tail risks. J Appl Econom 32(1):159–170
Duprey T (2018) Asymmetric risks to the economic outlook arising from financial system vulnerabilities. Technical report
Edison HJ (2003) Do indicators of financial crises work? An evaluation of an early warning system. Int J Finance Econ 8(1):11–53
Eichengreen B, Rose AK, Wyplosz C (1995) Exchange market mayhem: the antecedents and aftermath of speculative attacks. Econ Policy 10(21):249–312
EI-Shagi M, Knedlik T, von Schweinitz G (2013) Predicting financial crises: the (statistical) significance of the signals approach. J Int Money Finance 35:75–103
Frankel JA, Rose AK (1996) Currency crashes in emerging markets: an empirical treatment. J Int Econ 41(3/4):351–366
Frankel J, Saravelos G (2012) Can leading indicators assess country vulnerability? Evidence from the 2008–09 global financial crisis. J Int Econ 87:216–231
Girton L, Roper D (1977) A monetary model of exchange market pressure applied to the postwar Canadian experience. Am Econ Rev 67:537–548
Grimaldi MB (2010) Detecting and interpreting financial stress in the euro area. ECB Working Paper Series No. 1214, European Central Bank
Grimaldi MB (2011) Up for count? Central bank words and financial stress. Sveriges Riksbank Working Paper Series 252
Hanschel E, Monnin P (2005) Measuring and forecasting stress in the banking sector: evidence from Switzerland. BIS Paper No. 22, Bank for International Settlements
Hansen JL (2006) A risk index for euro-denominated assets. National Bank of Denmark Working Paper No. 36/2006
Hollo D, Kremer M, Duca ML (2012) CISS—a composite indicator of systemic stress in the financial system. ECB Working Paper Series No. 1426
Illing M, Liu Y (2006) Measuring financial stress in a developed country: an application to Canada. J Financ Stab 2(3):243–65
Islami M, Kurz-Kim J-R (2013) A single composite financial stress indicator and its real impact in the euro area. Discussion paper 31/2013, Deutsche Bundesbank
Kaminsky G, Lizondo S, Reinhart C (1998) Leading indicators of currency crises. IMF Working Paper No. 45 International Monetary Fund
Kim HH (2013) Forecasting macroeconomic variables using data dimension reduction methods: the case of Korea. BOK Working Paper 2013-26, Bank of Korea
Kim H, Shi W (2015) Forecasting financial market vulnerability in the U.S.: a factor model approach. Technical report, Auburn University
Louzis DP, Vouldis AT (2011) A financial systemic stress index for Greece. Presented at the first conference of the macro-prudential research (MaRs) network of the European System of Central Banks in Frankfurt am Main
McCracken MW (2007) Asymptotics for out of sample tests of Granger causality. J Econom 140:719–752
Misina M, Tkacz G (2009) Credit, asset prices, and financial stress. Int J Cent Bank 5:95–122
Morales MA, Estrada D (2010) A financial stability index for Colombia. Ann Finance 6(4):555–81
Oet MV, Eiben R, Bianco T, Gramlich D, Ong SJ (2011) The financial stress index: identification of system risk conditions. Working Paper No. 1130, Federal Reserve Bank of Cleveland
Sachs J, Tornell A, Velasco A (1996) Financial crises in emerging markets: the lessons from 1995. Brook Pap Econ Act 27(1):147–199
Sandahl J, Holmfeldt M, Rydén A, Strömqvist M (2011) An index of financial stress for Sweden. Sver Riksbank Econ Rev 2:49–67
Slingenberg JW, de Haan J (2011) Forecasting financial stress. DNB Working Paper No. 292 De Nederlandsche Bank
Stock JH, Watson MW (2002) Macroeconomic forecasting using diffusion indexes. J Bus Econ Stat 20(2):147–162
Tanner E (2002) Exchange market pressure, currency crises, and monetary policy; additional evidence from emerging markets. IMF Working Papers No. 02/14
van Roye B (2011) Financial stress and economic activity in Germany and the euro area. Kiel Working Paper No. 1743, Kiel Institute for the World Economy
Yiu MS, Ho W-YA, Jin L (2010) A measure of financial stress in Hong Kong financial market: the financial stress index. Hong Kong Monetary Authority Research Note No. 02/2010
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Kim, H., Shi, W. & Kim, H.H. Forecasting financial stress indices in Korea: a factor model approach. Empir Econ 59, 2859–2898 (2020). https://doi.org/10.1007/s00181-019-01744-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00181-019-01744-y
Keywords
- Financial stress index
- Principal component analysis
- PANIC
- In-sample fit
- Out-of-sample forecast
- Diebold–Mariano–West statistic