新冠疫情對匯率波動之實證研究

An Empirical Study of the COVID-19 on Exchange Rates Volatility

李愛玲(Ai- Ling Lee)

指導教授 ： 李顯峰

國立臺灣大學/社會科學院/經濟學研究所/碩士(2021年)

https://doi.org/10.6342/NTU202100748

摘要

本研究探討新冠疫情(COVID-19)對匯率波動率的影響，樣本期間為2010年1月至2020年6月之月資料，計有125個觀察值。採用GARCH(1,1)、TGARCH(1,1)、EGARCH(1,1)實證模型的波動性，分析COVID-19疫情對各國月平均外匯匯率波動的影響。採取ARCH效果檢定是以殘差平方的相關圖(Q)檢驗法，實證結果顯示COVID-19疫情在2020年1月至2020年6月的時間序列分析，在澳幣、加拿大幣、人民幣、歐元、英鎊、港幣、日圓、韓元、新台幣、新加坡幣兌美元的月平均匯率波動率其波動程度較大，各國月平均匯率波動率波動皆顯示於外匯市場存在著不對稱效果。
依據實證結果顯示，在GARCH建立波動性估計模型中，尤以GARCH(1,1)模型僅人民幣不符合共變異數條件，而在TGARCH(1,1)模型有微弱的非對稱性，但是在EGARCH(1,1)模型，人民幣在月平均匯率波動性極具非對稱性及存在槓桿效果。主要原因在於中國人行擴大貨幣政策力度及運用多種貨幣政策工具措施，穩定金融市場與減少疫情對企業的衝擊，以應對新冠疫情之影響。故針對各國樣本資料進行匯率波動性的模型評估中，以EGARCH 模型效果最好。

關鍵字

新冠疫情（COVID-19） ； 匯率波動 ； 時間序列分析 ； ARCH效果檢定 ； GARCH(1,1)模型 ； TGARCH(1,1)模型 ； EGARCH(1,1)模型

並列摘要

This study explores the impact of the COVID-19 pandemic on exchange rate volatility. The sample period is from January 2010 to June 2020, with 125 observations. Using the volatility of the empirical models of GARCH(1,1), TGARCH(1,1), and EGARCH(1,1), we analyze the impact of the COVID-19 epidemic on the fluctuations of the monthly average foreign exchange rates of various currencies. The ARCH effect test is based on the correlation diagram (Q) test method of residual squares. The empirical results show that the time series analysis of the COVID-19 epidemic from January 2020 to June 2020 is in Australian dollars, Canadian dollars, Renminbi (RMB), Euro, The monthly average exchange rate volatility of the British pound, Hong Kong dollar, Japanese yen, South Korean won, New Taiwan dollar, and Singapore dollar against the U.S. dollar fluctuates greatly. The fluctuations in the monthly average exchange rate volatility of various countries all show that there is an asymmetric effect in the foreign exchange market.
According to the empirical results, in the volatility estimation model established by GARCH, especially the GARCH(1,1) model only the RMB does not meet the covariance condition, while the TGARCH(1,1) model has weak asymmetry, but in the EGARCH(1,1) model, the monthly average exchange rate volatility of the RMB is extremely asymmetric and has a leverage effect. The main reason is that the People's Bank of China has expanded its monetary policy and used a variety of monetary policy tools and measures to stabilize the financial market and reduce the impact of the epidemic on enterprises by the COVID-19. Therefore, in the model evaluation of exchange rate volatility based on sample data of various countries, the EGARCH model has the best effect.

並列關鍵字

COVID-19 ； Exchange rate volatility ； Time series analysis ； ARCH effect test ； GARCH (1,1) model ； TGARCH (1,1) model ； EGARCH (1,1) model

參考文獻

英文部分:

1. Antonakakis, N. and J. Darby (2012), “Forecasting Volatility in Developing Countries' Nominal Exchange Returns”, MPRA Working Paper No.40875.

2. Black, F. (1976), “Studies of Stock Price Volatility Changes”, Proceedings of the 1976 Meeting of the Business and Economics Statistics Section, American Statistical Association, Washington DC, 177-181.

3. Bloom, D. E. and A. S. Mahal (1997), “Does the AIDS Epidemic Threaten Economic Growth? ”, Journal of Econometrics, 77, 105-124.

4. Bollerslev, T. (1986), “Generalized Autoregressive Conditional Heteroskedasticity”, Journal of Econometrics, 31(3), 307-327.