總體經濟基本面是否有助於匯率的預測?

Do Macroeconomic Fundamentals Help to Predict Exchange Rates？

林聖智(SHEN-CHIH LIN)

指導教授 ： 姚睿

國立中央大學/管理學院/經濟學系/碩士(2007年)

摘要

本篇論文使用Stock and Watson (2002) 所發展的動態因子模型(dynamic factor model, DFM) 針對台幣兌美元匯率進行預測, 目的在於重新探討總體經濟的基本面是否有助於匯率的預測。自從Meese and Rogoff (1983a) 這篇經典的研究發表後, 貨幣模型與總體變數應用在匯率預測方面的能力就不斷地遭受質疑。本文採用自臺灣以及美國總體變數所萃取出來的因子, 來進行匯率的預測。本文應用Clark and West (2007)所發展的針對涵蓋模型(nested model) 的大樣本檢定, 以及經濟價值(economic value) 來作為預測績效的評估準則。研究結果顯示, 在一至十二個月的預測期間下, 動態因子模型在統計與經濟兩項準則皆能擊敗作為標竿的 AR 模型。因此, 若能夠運用因子做為總體基本面的代理變數, 則總體基本面仍然有助於匯率的預測。

關鍵字

擴散指標 ； 涵蓋模型 ； 匯率預測 ； 經濟價值 ； 因子模型

並列摘要

This thesis uses the dynamic factor model (DFM) developed by Stock and Watson (2002) to forecast the NTD/USD exchange rate. The aim is to reinvestigate the usefulness of macroeconomic fundamentals in forecasting exchange
rates. The usefulness of structural monetary models and fundamentals has been in doubt since the seminal work of Meese and Rogoff (1983a). Both the macroeconomic variables of Taiwan and U.S. are used to extract factors for making predictions. The asymptotic test on nested models proposed by Clark and West (2007) and an economic value criterion are implemented. The DFM is shown to beat the benchmark AR model both in statistical criterion and economic value at horizons from 1 month to 12 months. We conclude that
macroeconomic fundamentals, with dynamic factors as their proxies, do help to predict exchange rates.

並列關鍵字

factor model ； exchange rate forecasting ； diffusion index ； economic value ； nested model

參考文獻

Abhyankar, A., Sarno, L., and Valente, G. (2005),“Exchange rates and fundamentals: evidence on the economic value of predicability.”, Journal of International Economics, 66(2), 325–348.

Artis, M., J., Banerjee, A., and Marcellino, M. (2005), “Factor forecasts for the UK”, Journal of Forecasting, 24, 279–298.

Bai, J. and Ng, S. (2002), “Determining the number of factors in approximate factor models”, Econometrica, 70, 191–221.

—(2006), “Evaluating latent and observed factors in macroeconomics and finance”, Journal of Econometrics, 131, 507–537.

Bernanke, B., S., Boivin, J., and Eliasz, P. (2005), “Measuring the effects of monetary policy: a factor-augmented vector autoregressive(FAVAR) approach.”, Quarterly Journal of Economics, 120(1), 387–422.