摘要
本論文包含關於應用時間序列的三個議題。 第一篇文章題目為「分析泰勒法則偏離」。這篇文章提供了一個新的方法估計泰勒法則中的參數。我們在前瞻 (forward-looking) 新興凱因斯模型中,納入了泰勒法則偏離。我們使用完全資訊下的最大概似估計法 (full information maximum likelihood, FIML) 估計模型中的參數, 其中所有的結構性衝擊皆假設服從 AR(1) 過程。在納入泰勒法則偏離後, 我們的模型可對利率、產出缺口以及通貨膨脹率之間的互動關係有更好的描述。此外,我們也使用其他的估計方法來確認新興凱因斯模型的有效性。本文結果顯示,我們可將利率法則分解成兩部份,系統性部份(可利用泰勒法則描述)以及隨機性部份(一般稱之為泰勒法則離差)。 第二篇文章題目為「石油市場與股票市場之間的互動關係」。本文利用 1990 年至 2015 年的週資料, 探討美國的石油市場與股票市場之間的互動關係。我們利用考慮異質變異數下的結構性自我相關迴歸模型,探討石油市場與股票市場在同一期間互相之影響。在控制可能同時影響石油與股票市場的衝擊,如石油供給衝擊、總合需求衝擊以及市場信心衝擊下, 我們發現石油價格衝擊對於股票市場有著顯著的正向影響。另一方面,我們發現股票市場衝擊對於石油價格有顯著的負向影響。 第三篇文章題目為「以股票報酬差異預測日匯率」。 透過檢驗短期匯率的預測能力,本文探討股票報酬是否具有預測未來匯率的資訊。受到未拋補股票平價假說之啟發,本文發現股票報酬差對於短期名目匯率(下交易日的匯率),在樣本內與樣本外期間皆具有預測能力。
並列摘要
This dissertation consists of three essays in applied time series econometrics. The first essay is entitled "Analyzing Taylor Rule Deviations". This study provides a resolution to identify the parameters of the Taylor rule. In particular, we introduce a deviation from the Taylor rule into a standard New Keynesian (NK) trinity model. We estimate the parameters in a canonical, pure forward-looking NK model with full information maximum likelihood (FIML) approach. All of the structural shocks are assumed to follow an AR(1) process. With inclusion of the deviation, our results show strong evidence that the estimated NK model offers a better explanation of the interactions among interest rates, the output gap, and inflation. In addition, we use different data sets and an alternative estimation approach to check the empirical validity of the NK trinity model.We provide strong evidence to show that the interest rate policy can be decomposed into two parts, a systematic part described by the Taylor rule and a nonsystematic component, which is known as Taylor rule deviations. The second essay is entitled "It Takes Two to Tango: The Interactions between Oil and Stock Markets". This essay uses weekly data from 1990 to 2015 to investigate the interactions between the crude oil market and the US stock market. In particular, we focus on contemporaneous bidirectional causality, using a structural vector autoregressive model with identification through heteroskedasticity. After accounting for common shocks including oil supply shocks, global aggregate demand shocks, and market sentiment shocks, it is found that oil price shocks have a significantly positive impact on the stock market. On the other hand, we find significantly negative responses of crude oil prices to the US stock market shocks. The third essay is entitled "Forecasting Daily Exchange Rates with Stock Return Differentials". This essay examines short-horizon exchange rate predictability and investigates whether stock returns contain information for forecasting daily exchange rate movements. Inspired by the uncovered equity parity condition, we show that stock return differentials have strong in-sample and out-of-sample predictive power for nominal exchange rates with short horizons (one-day-ahead predictions).
參考文獻
延伸閱讀
- Lu, C. H. (2008). 貨幣經濟學在最適成長模型之三篇論文 [doctoral dissertation, National Taiwan University]. Airiti Library. https://doi.org/10.6342/NTU.2008.00280
- 黃馥珍、卓紋君（2009）。敘說研究的探索從三本敘說分析研究的比較說起。輔導季刊，45(3)，49-64。https://doi.org/10.29742/GQ.200909.0006
- 黃紫惟（2019）。運用三種分類法標示資料集之研究〔碩士論文，逢甲大學〕。華藝線上圖書館。https://doi.org/10.6341/fcu.M0607050
- 陳玟伶（2001）。以三維序列表示法為基礎之空間規劃演算法〔碩士論文，中原大學〕。華藝線上圖書館。https://doi.org/10.6840/cycu200100042
- Lin, Z. (2009). On the statistical inference of some nonlinear time series models [master's thesis, The University of Hong Kong]. Airiti Library. https://www.airitilibrary.com/Article/Detail?DocID=U0029-1812201200016710