本研究以臺灣加權股價指數期貨日內逐筆委託簿資料為樣本，使用向量自我迴歸模型(VAR)，藉由Granger因果檢定、衝擊反應函數、預測誤差變異數分解和共整合檢定等分析工具研究不同觀察頻率下委託單量不平衡的程度(Volume Order Imbalance, VOI)與報酬率間的連動關係。實證結果發現，在觀察頻率較高時(時間間隔約為0.1秒等級)，VOI和報酬率的領先落後關係並不明顯，但如只觀察VOI超過特定臨界值的樣本則可發現較為極端的VOI對報酬率具有較佳的解釋力；在中級的觀察頻率下(時間間隔在約為30秒等級)，VOI領先報酬率的現象有顯著的提升，且取VOI的極端值也同樣能提高其解釋力；而在較低的觀察頻率下(時間間隔約為300秒等級)，VOI和報酬率呈現雙向回饋關係，且解釋力明顯高於高頻和中頻的情況，但VOI臨界值在此高頻的情況下已不具影響力。

In this thesis, the intraday price data of futures on Taiwan’s weighted stock price index are taken as a sample, and the vector autoregressive (VAR) model with a number of analytical tools such as Granger causality test, impulse response function, forecast error variance decomposition, and co-integration test are used to investigate the relation between the volume order imbalance (VOI) and the rates of return under different frequencies. The empirical results show that when observation frequency is high (at mini-second level), the leading and lagging relation between VOI and the rates of return is not obvious. But if the data of extreme values of VOI are collected, the explanatory power of VOI on the rates of return can be significantly increased. When the observation frequency is at the intermediate level (time intervals are about 30 seconds), the phenomenon that VOI leads the rates of return becomes more prominent, and the extreme straightness of VOI can also improve its explanatory power. When observation frequency is low (time intervals are about 300 seconds ), VOI and the rates of return show an interactive relation with bidirectional feedback, and the explanatory power is significantly higher than that of high and intermediate frequencies, but the extreme values of VOI provides little influence in the low frequency case.

1. 柯美珠、蕭慧玲、邱敬貿(2006)，市場深度、價差與委託單不均衡之關聯分析，績效與策略研究，第三卷第二期，129-156頁。
2. 陳旭昇 (2013)，時間序列分析-總體經濟與財務金融之應用。
3. 黃玉娟、林明白（2003），買賣單失衡、價差和報酬之探討：以臺指期貨在臺灣期貨交易所及新加坡交易所為例。財務金融學刊， 11（2），71-98。DOI： 10.6545/JFS.2003.11(2).3
4. 鍾惠民、周賓凰和孫而音（2014），「財務計量EViews的運用」，修訂版。
5. Arévalo A., Niño J., Hernández G., Sandoval J. (2016) High-Frequency Trading Strategy Based on Deep Neural Networks. In: Huang DS., Han K., Hussain A. (eds) Intelligent Computing Methodologies. ICIC 2016. Lecture Notes in Computer Science, vol 9773. Springer, Cham
6. Álvaro Cartea & Sebastian Jaimungal (2013) Modelling Asset Prices for Algorithmic and High-Frequency Trading, Applied Mathematical Finance, 20:6, 512-547, DOI: 10.1080/1350486X.2013.771515
7. Chien, Yi Ju. (2019). Dynamic Limit Order Book of Taiwan Stock Exchange Capitalization Weighted Stock Index Futures by R.
8. Chordia, Tarun and Roll, Richard and Subrahmanyam, Avanidhar (2002) Order imbalance, liquidity, and market returns. Journal of Financial Economics, 65 (1). pp. 111-130. ISSN 0304-405X.
9. Cornell, Bradford. (2006). The Relationship Between Volume and Price Variability in Futures Markets. Journal of Futures Markets. 1. 303 - 316. 10.1002/fut.3990010303.
10. Dickey, D.A. & Fuller, W.A. (1979) Distribution of the Estimator for Autoregression Times Series Unit Root. Journal of American Statistical Association 74, 724-732
11. Engle, R.F. & C.W.J. Granger (1987) Cointegration and error correction: Representation, estimation and testing. Econometrica 55, 251-276
12. Granger, C.W.J & N.R. Swanson (1997) An introduction to stochastic unit root processes. Journal of Econometrtics 80, 35-62
13. Hendershott, T., Jones, C. M., & Menkveld, A. J. (2011). Does algorithmic trading improve liquidity?. The Journal of Finance, 66(1), 1-33
14. Jarnecic, E. & M. Snape (2014), The Provision of Liquidity by High-Frequency Participants, The Financial Review, Vol. 49, Issue 2, 371–394 : May 2014
15. Karpoff, J. (1987). The Relation between Price Changes and Trading Volume: A Survey. Journal of Financial and Quantitative Analysis, 22(1), 109-126. doi:10.2307/2330874
16. Kwiatkowski, D., P.C.B. Phillips, P. Schmidt, & Y. Shin (1992) Testing the null of stationarity against the alternative of a unit root: How sure are we that economic time series have a unit root? Journal of Econometrics 54, 159-178
17. Phillips, P.C.B. & Perron, P. (1988) Testing for a unit root in time seires regression. Biometrika 75, 335-346
18. Rama Cont, Arseniy Kukanov, and Sasha Stoikov. The price impact of order book events. Journal of Financial Econometrics, 12(1):47–88, 2014.
19. Sheng, D. (2015). Order Imbalance Based Strategy in High Frequency Trading . Master’s thesis, Oxford University. An optional note.
20. Sims, C. A. (1980), “Macroeconomics and Reality”, Econometrica, 48, 1-48