Abstract
This paper applies the growth-at-risk framework proposed by Adrian et al. (2019) to Singapore, an international financial centre whereby financial shocks are intermediated away quickly. We gauge near-term risks around growth projections taken from the survey of professional forecasters by accounting for financial stress in both local and global financial markets, as well as worldwide economic uncertainty. The conditioning variables are first linked to future growth through quantile regressions, and the estimated quantiles are fitted with skew t-distributions to produce full predictive distributions. Scenario analysis reveals that greater local financial strain tends to widen the uncertainty of growth outlook, higher global financial stress portends more severe recessions, while increased uncertainty in the economic policy environment dampens the intensity of economic booms. We also document higher average log predictive scores for conditional distributions compared to unconditional ones when projecting one and two quarters ahead. Our empirical results underscore the importance of incorporating the influence of foreign vulnerabilities in addition to domestic ones to assess short-term growth risk in an international financial centre like Singapore.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Notes
Apart from applying to individual countries for monitoring output stability, the growth-at-risk analysis has been adapted to predict downside risks to future house prices (Adrian et al. (2020)) as well as to study the effectiveness of macroprudential policies. On the latter, see Suarez (2021), Ong et al. (2022) and Patra et al. (2022), amongst others.
Official GDP growth forecasts are not used as these are reported as ranges of possible values in Singapore.
Chow and Choy (2023) showed that the growth projections of these professional forecasters have higher accuracy than those generated from an autoregressive model that relies only on past GDP values.
Survey participants are also requested to forecast other macroeconomic variables and the various components of GDP. However, only the current quarter forecasts are available from 1999Q4. The one-quarter ahead forecasts for these variables only began in 2017Q4. Consequently, there are insufficient data points to extend our empirical analysis to these alternative target variables until more data from future surveys become available.
Although four-quarter ahead forecasts can be approximated from the fixed event SPF forecasts following Dovern et al. (2012), we found poor density forecast performance when projecting one year ahead. This suggests that the predictive content from the professional forecasts and the conditioning variables is primarily short term. Detailed results are available upon request.
Meanwhile, three-step ahead forecasts are missing from all second-quarter and third-quarter surveys. We do not interpolate this series as the limited information in the surveys would likely yield inaccurate approximations.
A lower stock market return or a higher stock market volatility suggests a loss of investor confidence, while a higher bank beta means the bank’s stock is more sensitive to market movements, indicating higher uncertainty in investing in the banking sector. A rising exchange market pressure index reflects a greater stress level in the foreign exchange market. Finally, a widening sovereign debt spread between the 10- and 2-year government bonds implies a higher default risk or lower credit quality.
Regional financial stress indexes, available from the ADB, have high pairwise correlations with SFSI (at least 0.8). Since the information content in the regional indexes overlaps significantly with the domestic index, we exclude them from the model to avoid multicollinearity problems.
In times of financial stress, credit spreads tend to widen with greater default risk and funding in financial institutions tends to tighten with higher counterparty risk or liquidity risk. At the same time, investors switch from risky to safe assets, raising their valuation. Meanwhile, greater volatility in the various financial markets reflects greater risk in investing in these markets.
Other indexes, like the world uncertainty index proposed by Ahir et al. (2018) and the geopolitical risk index proposed by Caldara and Iacoviello (2022), were also considered. However, we decided not to include them as conditioning variables as they do not have an evident leading relation with Singapore’s output growth.
We do not use a Singapore-specific EPU index as it closely tracks the global uncertainty index with a correlation of 0.99.
As robustness checks, we examine the quantile regression coefficients for the pre-pandemic period, i.e. 2003Q4 to 2019Q4. The results are qualitatively similar for all cases except for EPU at h = 2, where the downward shift in the right tail for EPU is not evident. Detailed results are available upon request.
Because of its publication lag, the SFSI recorded only a moderately high level of 2.8 in 2008Q4 but shot up in the next quarter to register 8.8 in 2009Q1.
We also performed scenario analysis of single-variable models. Compared to the multivariable model, the corresponding counterfactual distributions from single-indicator models tend to have larger scale parameters and heavier left skew. In all cases, a two-standard deviation shock to the respective conditioning variable shifted the one- and two-quarter ahead growth distributions such that GAR5% is lowered. Detailed results are available upon request.
This result for h = 2 corresponds to the significantly positive regression coefficients at the lower quantiles found in Sect. 3.
As noted by one of the referees, starting the out-of-sample forecasting period in 2013Q4 excludes two key stress events in our sample: the global financial crisis and the European sovereign debt crisis. This omission makes the comparison across different models less informative.
References
Adams PA, Adrian T, Boyarchenko N, Giannone D (2021) Forecasting macroeconomic risks. Int J Forecast 37:1173–1191
Adrian T, Boyarchenko N, Giannone D (2019) Vulnerable growth. Am Econ Rev 109(4):1263–1289
Adrian T, Deghi A, Katagiri M, Shahid S, Valckx N (2020) Predicting downside risks to house prices and macro-financial stability. IMF Working Paper 2020/011
Ahir H, Bloom N, Furceri D (2018) The world uncertainty index. NBER Working Paper 29763
Azzalini A, Capitanio A (2003) Distributions generated by perturbation of symmetry with emphasis on a multivariate skew t-distribution. J Royal Stat Soc Series B Stat Methodol. 65:367–389
Baker SR, Bloom N, Davis S (2016) Measuring economic policy uncertainty. Q J Econ 131(4):1593–1636
Brunnermeier MK, Sannikov Y (2014) A macroeconomic model with a financial sector. Am Econ Rev 104:379–421
Busetti F, Caivano M, Monache DD, Pacella C (2021) The time-varying risk of Italian GDP. Econ Model. 101:105522
Caldara D, Iacoviello M (2022) Measuring geopolitical risk. Am Econ Rev 112(4):1194–1225
Chow HK (2017) Volatility spillovers and linkages in the Asian stock markets. Emerg Mark Financ Trade 53(12):2770–2781
Chow HK (2021) Connectedness of Asia pacific forex markets: China’s growing influence. Int J Financ Econ 26(3):3807–3818
Chow HK, Choy KM (2023) Economic forecasting in a pandemic: some evidence from Singapore. Empir Econ 64(5):2105–2124
Davis S (2016) An index of global economic policy uncertainty. Mon Auth Singap Macroecon Rev 5(2):91–97
Dovern J, Fritsche U, Slacalek J (2012) Disagreement among forecasters in G7 countries. Rev Econ Stat 94(4):1081–1096
Ghosh S, Kamate V, Sonpatki R (2023) Application of growth-at-risk framework for Indian GDP. Reserve Bank of India Bulletin, March
International Monetary Fund (2017) Financial conditions and growth at Risk, Global Financial Stability Report Chapter 3, October
IMF (2018) Singapore article IV consultation staff report. IMF Country Report 18/274, September.
Koenker R (2005) Quantile regression. Cambridge University Press
Koenker R, Bassett G (1978) Regression quantiles. Econometrica 46:33–50
Lafarguette R (2019) Growth at risk tool: technical appendix. Unpublished mimeo, International Monetary Fund
Lloyd S, Manuel E, Panchev K (2024) Foreign vulnerabilities, domestic risks: the global drivers of GDP-at-risk. IMF Econ Rev 72(1):335–392
Monetary Authority of Singapore (2019) Special study 1: financial conditions index, financial vulnerability index and growth-at-risk for Singapore. Financial Stability Review November
Monin PJ (2019) The OFR financial stress index. Risks 7(1):25
Muduli S, Behera H, Patra MD (2022) Capital flows at risk: India’s experience. RBI Bulletin 76(6):73–88
Ong LL, Yiu M, Gabriella LG (2022) Capital flow management and macroprudential policy measures in the ASEAN+3: initial recommendations. AMRO Position Policy Paper PPP/22–01, March.
Park CY, Mercado R (2014) Determinants of financial stress in emerging market economies. J Bank Finance 45:199–224
Prasad A, Elekdag S, Jeasakul P, Lafarguette R, Alter A, Feng AX, Wang C (2019) Growth at risk: concept and application in IMF country surveillance. IMF Working Paper 2019/036
Reifschneider D, Tulip P (2019) Gauging the uncertainty of the economic outlook using historical forecasting errors: the federal reserve’s approach. Int J Forecast 35:1564–1582
Suarez J (2021) Growth-at-risk and macroprudential policy design. European Systemic Risk Board Occasional Paper 19, September.
Acknowledgements
The author is grateful for constructive suggestions from the associate editor and two journal referees, which significantly improved the paper. She would also like to thank Changchun Wang for advice on the GAR tool provided by the IMF, as well as Colin Kwong and Jordan Lee for excellent research assistance.
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
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Chow, H.K. Gauging growth risk in an international financial centre: some evidence from Singapore. Empir Econ 68, 2199–2224 (2025). https://doi.org/10.1007/s00181-024-02705-w
Received:
Accepted:
Published:
Version of record:
Issue date:
DOI: https://doi.org/10.1007/s00181-024-02705-w