中国权证市场微观结构研究
|
摘要
权证是一种赋予持有人在约定时间内有权按约定价格向发行人购入或者出售合同规定的标的证券的凭证,是成熟证券市场比较流行的金融工具。随着全球范围内权证市场的兴起,作为一种重要的衍生工具,针对权证的定价、风险管理以及市场微观结构的研究日渐成为关注焦点。
市场的微观结构是从微观的角度去研究金融市场的特性和内在规律,已成为当今金融研究领域的热点之一。波动性和流动性作为金融市场最重要的特性,已成为反映市场质量和效率的最重要的指标,并始终贯穿整个市场微观结构理论。
针对市场微观结构的研究,依靠低频交易数据已经不能满足研究的需要。伴随着现代计算机技术的发展,高频数据逐渐被研究者们应用到对市场微观结构的研究中。实证研究表明,利用高频数据针对市场的波动性和流动性展开建模分析具有优良的特性。
本论文首先介绍了中国权证市场发展状况和金融高频数据的研究进展,接着回顾了微观结构的研究内容和国内外的研究现状,随后分别就波动性和流动性展开理论探索和实证研究,得出结论。
针对波动性,本论文首先介绍了波动性的定义、特征和估计模型,然后选取中国权证市场的13只权证,利用分时高频交易数据,提取价格收益率序列,建立了相应的GARCH模型,随后,又结合IGARCH和TGARCH模型针对市场上存在的不对称效应进行了分析。
针对流动性,首先介绍了流动性的概念、度量以及ACD估计模型,在此基础上,利用权证的分笔高频交易数据,选取交易量持续期这一指标来刻画流动性,经过数据处理和交易量持续期的提取,对模型的有效性、分布假设进行了充分的研究和探讨。根据研究结果可以判断,ACD模型在分析权证市场的微观结构方面具有非常好的表现。进一步我们将新的微观结构变量加入原先模型中,构造了以检验市场微观结构假设的扩展ACD模型,并对市场微观结构理论的几个重要假设进行了实证检验,检验表明平均交易量和买卖价差因子对市场流动性具有显著负面效应。
本文的研究表明：GARCH模型及其扩张的IGARCH模型可以很好地模拟权证市场的波动性,证明了权证市场的波动存在明显的集聚性,并且这种波动在一定程度上是非对称的。ACD模型和SCD模型可以很好地模拟权证市场的流动性。模型拟合结果表明权证市场的交易量持续期存在明显的集聚现象,ACD和SCD模型可以很好地对此予以解释。综合考虑模型估计和残差检验,对数GACD模型和SCD模型是流动性拟合效果最好的两种模型,根据拟合出的模型就可以对权证的波动性和流动性进行预测。根据研究结果,我们有针对性地提出了一些政策建议,通过改革交易机制、设定创设资产规模限制、发展权证新品种等措施,可以在一定程度上减少波动集聚和提升流动性,从而实现权证市场的健康发展。
A warrant is a security that entitles the holder to buy stock of a company that issued at a specified price within the certain time, it's one of the most popular financial instruments in developed security market. As the market developing, the research on the pricing, risk management and microstructure of warrant has become the focus of researchers.
Market microstructure is about research on the features and patterns of financial market, which is becoming the hotspot of finacial fields. Volatility and liquidity have been the most important indicators of market quality and efficiency as they are the most important features of financial market.
Researches in the market microstructure focus on the processes of discovering the trading prices and the operating mechanisms of the trading prices. Low frequency trading data is far from enough for this kind of researches. With the rapid development of computer science, it makes possible for people to explore the market microstructure with high frequency data. The empirical researches indicate that the model constructed for volatility and liquidity exhibits superior features in dealing with the high frequency financial data.
In this paper, we first introduce the development of the warrant market of Chinese mainland and the application of high frequency financial data, then give a review of the research on the market microstructure, after that, we conduct empirical researches for volatility and liquidity.
For volatility research, we first introduce the definiton and features of volatility, then with the time sharing high frequency data of 13 warrants of mainland market, we build the GARCH model by price return series. Besides, we analyze the asymmetric effect with the combination of IGARCH and TGARCH model.
For liquidity research, we first take a brief review of the related literature about liquidity. Then we introduce econometric models used in the research including the linear and nonlinear model with different distributions. As a consequence, the paper constructs and analyzes the duration of 13 selected warrants from Chinese mainland warrant market with the ACD model introduced. Then, the empirical research is conducted to identify the reasonable distribution of the model. The empirical result indicates that the ACD model does a good job in analyzing the high frequency data of warrants. With external variables of market microstructure and an extended ACD model, the empirical research confirms some important hypothesis of the microstructure of Chinese financial market.
We have found from the results that the GARCH model and the extended IGARCH fit the volatility of warrant well, which prove the existence of volatility clustering with asymmetric effect. Besides, the ACD model and SCD model have a good fitting for the liquidity of Chinese mainland warrant market. The model can also explain the volatility clustering of trading volume duration exactly. Among all the models, Log-GACD model and SCD model are the most fitted if we consider the results of model estimation and residual test. We give some advice for warrant market supervisor based on the research result. By trade mechanism reform, restriction on the asset size, development of new class warrant, we can reduce the volatility clustering and improve the market liquidity, then achieve the stable development of warrant market.
市场的微观结构是从微观的角度去研究金融市场的特性和内在规律,已成为当今金融研究领域的热点之一。波动性和流动性作为金融市场最重要的特性,已成为反映市场质量和效率的最重要的指标,并始终贯穿整个市场微观结构理论。
针对市场微观结构的研究,依靠低频交易数据已经不能满足研究的需要。伴随着现代计算机技术的发展,高频数据逐渐被研究者们应用到对市场微观结构的研究中。实证研究表明,利用高频数据针对市场的波动性和流动性展开建模分析具有优良的特性。
本论文首先介绍了中国权证市场发展状况和金融高频数据的研究进展,接着回顾了微观结构的研究内容和国内外的研究现状,随后分别就波动性和流动性展开理论探索和实证研究,得出结论。
针对波动性,本论文首先介绍了波动性的定义、特征和估计模型,然后选取中国权证市场的13只权证,利用分时高频交易数据,提取价格收益率序列,建立了相应的GARCH模型,随后,又结合IGARCH和TGARCH模型针对市场上存在的不对称效应进行了分析。
针对流动性,首先介绍了流动性的概念、度量以及ACD估计模型,在此基础上,利用权证的分笔高频交易数据,选取交易量持续期这一指标来刻画流动性,经过数据处理和交易量持续期的提取,对模型的有效性、分布假设进行了充分的研究和探讨。根据研究结果可以判断,ACD模型在分析权证市场的微观结构方面具有非常好的表现。进一步我们将新的微观结构变量加入原先模型中,构造了以检验市场微观结构假设的扩展ACD模型,并对市场微观结构理论的几个重要假设进行了实证检验,检验表明平均交易量和买卖价差因子对市场流动性具有显著负面效应。
本文的研究表明：GARCH模型及其扩张的IGARCH模型可以很好地模拟权证市场的波动性,证明了权证市场的波动存在明显的集聚性,并且这种波动在一定程度上是非对称的。ACD模型和SCD模型可以很好地模拟权证市场的流动性。模型拟合结果表明权证市场的交易量持续期存在明显的集聚现象,ACD和SCD模型可以很好地对此予以解释。综合考虑模型估计和残差检验,对数GACD模型和SCD模型是流动性拟合效果最好的两种模型,根据拟合出的模型就可以对权证的波动性和流动性进行预测。根据研究结果,我们有针对性地提出了一些政策建议,通过改革交易机制、设定创设资产规模限制、发展权证新品种等措施,可以在一定程度上减少波动集聚和提升流动性,从而实现权证市场的健康发展。
A warrant is a security that entitles the holder to buy stock of a company that issued at a specified price within the certain time, it's one of the most popular financial instruments in developed security market. As the market developing, the research on the pricing, risk management and microstructure of warrant has become the focus of researchers.
Market microstructure is about research on the features and patterns of financial market, which is becoming the hotspot of finacial fields. Volatility and liquidity have been the most important indicators of market quality and efficiency as they are the most important features of financial market.
Researches in the market microstructure focus on the processes of discovering the trading prices and the operating mechanisms of the trading prices. Low frequency trading data is far from enough for this kind of researches. With the rapid development of computer science, it makes possible for people to explore the market microstructure with high frequency data. The empirical researches indicate that the model constructed for volatility and liquidity exhibits superior features in dealing with the high frequency financial data.
In this paper, we first introduce the development of the warrant market of Chinese mainland and the application of high frequency financial data, then give a review of the research on the market microstructure, after that, we conduct empirical researches for volatility and liquidity.
For volatility research, we first introduce the definiton and features of volatility, then with the time sharing high frequency data of 13 warrants of mainland market, we build the GARCH model by price return series. Besides, we analyze the asymmetric effect with the combination of IGARCH and TGARCH model.
For liquidity research, we first take a brief review of the related literature about liquidity. Then we introduce econometric models used in the research including the linear and nonlinear model with different distributions. As a consequence, the paper constructs and analyzes the duration of 13 selected warrants from Chinese mainland warrant market with the ACD model introduced. Then, the empirical research is conducted to identify the reasonable distribution of the model. The empirical result indicates that the ACD model does a good job in analyzing the high frequency data of warrants. With external variables of market microstructure and an extended ACD model, the empirical research confirms some important hypothesis of the microstructure of Chinese financial market.
We have found from the results that the GARCH model and the extended IGARCH fit the volatility of warrant well, which prove the existence of volatility clustering with asymmetric effect. Besides, the ACD model and SCD model have a good fitting for the liquidity of Chinese mainland warrant market. The model can also explain the volatility clustering of trading volume duration exactly. Among all the models, Log-GACD model and SCD model are the most fitted if we consider the results of model estimation and residual test. We give some advice for warrant market supervisor based on the research result. By trade mechanism reform, restriction on the asset size, development of new class warrant, we can reduce the volatility clustering and improve the market liquidity, then achieve the stable development of warrant market.
引文
[1]屈文洲,吴世农.2002.中国股票市场微观结构的特征分析——卖报价价差模型及影响因素的实证研究[J].经济研究,1：56-63.
[2]房振明.2004.基于时间特性的中国股市波动密度特征研究[J].北京科技大学学报：社会科学版,4：28-31.
[3]郭兴义,杜本峰,何龙灿.2002.(超)高频数据分析与建模[J].统计研究,11：28-31.
[4]常宁,徐国祥.2004.金融高频数据分析的现状与问题研究[J].财经研究,3：31-39.
[5]周建,潘惠峰.2004.金融计量学的理论体系及其新进展[J].哈尔滨工业大学学报：社会科学版,3：93-99.
[6]史美景.2004.高频数据及市场微观结构模型[J].统计与决策,10：155-156.
[7]马超群,张明良.2005.ACD族计量模型的分类与比较分析[J].金融经济,8：86-87.
[8]陈敏,王国明,吴国富等.2003.中国证券市场的ACD-GARCH模型及其应用[J].统计研究,11：60-62.
[9]蒋学雷,陈敏,王国明等.2004.股票市场的流动性度量的动态ACD模型[J].统计研究,4：42-44.
[10]黄杰琨.2003.电子指令驱动市场上的交易持续期与知情者交易的相关研究[D]：[博士].厦门：厦门大学,3-8.
[11]屈文洲.2004.限价委托交易系统中行情公告牌的信息含量与交易者行为分析[D]：[博士].厦门：厦门大学,2-25.
[12]吴武泽.2002.基于ACD-GARCH模型的股票流动性分析[D]：[博士].北京：对外经济贸易大学,1-70.
[13]蒋学雷.2003.中国股票市场有关问题的统计分析与实证研究：[D]：[博士].北京：中国科学院数学与系统科学研究院,49-80.
[14]张国勇.2004.金融市场(超)高频数据建模及其实证分析：[M]：[硕士].天津：天津大学,8-52.
[15]陈炜.2005.中国股票市场交易和价格久期的研究-基于高频数据的自回归条件久期模型[2009-2-12].http://test.ccfr.org.cn.
[16]刘逖.2002.市场微观结构与交易所竞争战略[M].上海：上海证券交易所综合研究室,1-183.
[17]史代敏.2002.沪深股市股指波动的协整性研究[J].数量经济技术经济研究,9：103-105.
[18]戴国强、吴林祥.1999.金融市场微观结构理论上海[M].上海：上海财经大学出版社.
[19]房振明,王春峰.2004.上海股票市场收益日内效应的研究[J].北京理工大学学报：社会科学版,6：38-41.
[20]王艳秋.2008.我国内地与香港地区权证市场发展之比较[J].黑龙江对外经贸,8：42-53.
[21]房振明,王春峰.2005.基于不规则数据的中国股市微观结构研究[J].系统工程学报,2：89-93.
[22]补冯林,张卫国,何伟.2005.基于超高频数据的股票流动性度量研究[J].统计与决策,2：24-26.
[23]张晖.2007.香港权证市场发展给内地的启示[J].南方金融,6：21-23.
[24]胡朝晖.2006.中国权证市场的发展路径[J].特区经济,3：35-38.
[25]马超群,张明良.2006.中国证券市场的LOG-ACD模型及其应用研究[J].统计与决策,2：43-46.
[26]毛崇峰.2004.股票市场流动性风险度量方法及其实证研究[M]：[硕士].湖南：湖南大学工商管理学院,16-24.
[27]詹场,胡星阳.2001.流动性衡量方法之综合评论[J].国家科学委员会研究汇刊：人文及社会科学(台湾),11(3)：205-221.
[28]纪路,陈伟忠.2002.市场微观结构及其对市场流动性的影响分析[J].财经问题研究,9：14-16.
[29]王晶,王玉玲,向东进等.2006.自回归条件持续期(ACD)模型研究[J].统计与决策,6：42-43.
[30]仲黎明,刘海龙,吴冲锋.2003.中国股票市场流动性：过高还是过低[J].当代经济科学,3：58-61.
[31]王晶,王玉玲,向东进.2007.自回归条件持续期(ACD)模型的统计特性分析[J].汉江大学学报,6：23-24.
[32]耿克红,张世英.2008.超高频数据下金融市场持续期序列模型述评[J].中国管理科学,8：16-20.
[33]Engle,R.F.,Russell, J. R.1998. Autoregressive conditional duration:A New model for irregularly-spaced transaction data [J].Econometrica 66, a:1127-1162.
[34]Bauwens.L.,Giot,.2000. The logarithmic ACD model:An application to the bid-ask quote process of three NYSE stocks[J].Annalesd'Economieet de Statistique,60:117-150.
[35]Lunde, A.1999. A generalized gamma autoregressive conditional duration model[C]. University of Aarhusr:1-20.
[36]Fernandes,M.,Grammig, J.2003. A Familiy of Autoregressive Conditional Duration Models[C].Graduate School of Economics.Getulio Vargas and CORE Discussion Paper:1-20.
[37]Hentschel, L.1995. All in the family:Nesting symmetric and asymmetric GARCH models [J]. Journal of Financial Economics,39:71-104.
[38]Zhang, M. Y, Russell, J. R., Tsay, R. S.2001. A nonlinear autoregressive conditional duration model with applications to financial transaction data [J].Journal of Econometrics,104:179-207.
[39]McInish T, R Wood.1992. An Analysis of Intraday Patterns in Bid/Ask Spreads for NYSE Stocks.Journal of Finance,47(2):753-764
[40]Engle R F.2000. The econometrics of ultra-high-frequency data.Econometrica, 68(1):1-22.
[41]Shleifor A.2000. In Efficient markets:An Introduction to Behavioral Finance [working paper].Oxford University:1-18.
[42]Engle R F, Jeffrey R Russell.1994. Forecasting Transaction Rates:The Autoregressive Conditional Duration Model:[working paper].Cambridge:5-40.
[43]Luc Bauwens, Pierre Giot.2000. Asymmetric ACD models:introducing price information in ACD models with a two state transition model:[discussion paper].University catholique de Louvain, Louvain-La-Neuve:1-24.
[44]Antonio Cosma, Fausto Galli.2004. A Nonparammtric ACD Model:[discussion paper].University of Lugano:1-24.
[45]Russell, Jeffrey R Engle.1998. Econometric Analysis of Discrete Valued, Irregulalry spaced Financial Transactions Data Using a New Autoregressive Conditional Multinomial Model:[working paper].University of Chicago,Graduate School of Business:1-31.
[46]Ghysels E, Gourieroux C, Jassik J.2004. Stochastic volatility duration models. Journal of Econometrics,119(2):413-433.
[47]Bauwens L, Giot P.2000. Modeling and predicting intra-day price movements in stock markets with autoregressive conditional duration Models:[working paper].Universit'e Catholique de Louvain:5-23.
[48]Yanhui Liu, Yongmiao Hong, Shouyang Wang.2005. How well can Autoregressive Duration Models Capture the Price Durations Dynamics of Foreign Exchanges.[2009-5-12].http://www.ccfr. org.cn.
[49]Lunde A.2000. A generalized gamma autoregressive conditional duration model: [Working paper].Aarlborg University:4-17.
[50]Gramming J, Maurer K O.2000. Non-monotonic hazard function and the autoregressive conditional duration model.The Econometrics Journal,3(1):16-38.
[51]Engle R F, Russel J.1997. Forecasting the frequency of changes in quoted foreign exchange prices with the autoregressive conditional duration model. Journal of Empirical Finance,4(2):187-212.
[52]Easley, O'Hara, Maureen.1992. Time and the process of security price adjustment. Journal of Finance,47(2),577-606.
[53]Rober F Engle, Joe Lange.2001. Predicting VNET:A model of the dynamics of market depth. Journal of Financial Markets,4(2):113-142.
[54]Dufour A, Engle R F.2000. Time and the price impact of a trade.Journal of Finance,55(6):2467-2498.
[55]Zumbach G O.2005. Considering time as the random variable:the first hitting time.[2009-5-18]. http://ssrn.com/abstract.
[2]房振明.2004.基于时间特性的中国股市波动密度特征研究[J].北京科技大学学报：社会科学版,4：28-31.
[3]郭兴义,杜本峰,何龙灿.2002.(超)高频数据分析与建模[J].统计研究,11：28-31.
[4]常宁,徐国祥.2004.金融高频数据分析的现状与问题研究[J].财经研究,3：31-39.
[5]周建,潘惠峰.2004.金融计量学的理论体系及其新进展[J].哈尔滨工业大学学报：社会科学版,3：93-99.
[6]史美景.2004.高频数据及市场微观结构模型[J].统计与决策,10：155-156.
[7]马超群,张明良.2005.ACD族计量模型的分类与比较分析[J].金融经济,8：86-87.
[8]陈敏,王国明,吴国富等.2003.中国证券市场的ACD-GARCH模型及其应用[J].统计研究,11：60-62.
[9]蒋学雷,陈敏,王国明等.2004.股票市场的流动性度量的动态ACD模型[J].统计研究,4：42-44.
[10]黄杰琨.2003.电子指令驱动市场上的交易持续期与知情者交易的相关研究[D]：[博士].厦门：厦门大学,3-8.
[11]屈文洲.2004.限价委托交易系统中行情公告牌的信息含量与交易者行为分析[D]：[博士].厦门：厦门大学,2-25.
[12]吴武泽.2002.基于ACD-GARCH模型的股票流动性分析[D]：[博士].北京：对外经济贸易大学,1-70.
[13]蒋学雷.2003.中国股票市场有关问题的统计分析与实证研究：[D]：[博士].北京：中国科学院数学与系统科学研究院,49-80.
[14]张国勇.2004.金融市场(超)高频数据建模及其实证分析：[M]：[硕士].天津：天津大学,8-52.
[15]陈炜.2005.中国股票市场交易和价格久期的研究-基于高频数据的自回归条件久期模型[2009-2-12].http://test.ccfr.org.cn.
[16]刘逖.2002.市场微观结构与交易所竞争战略[M].上海：上海证券交易所综合研究室,1-183.
[17]史代敏.2002.沪深股市股指波动的协整性研究[J].数量经济技术经济研究,9：103-105.
[18]戴国强、吴林祥.1999.金融市场微观结构理论上海[M].上海：上海财经大学出版社.
[19]房振明,王春峰.2004.上海股票市场收益日内效应的研究[J].北京理工大学学报：社会科学版,6：38-41.
[20]王艳秋.2008.我国内地与香港地区权证市场发展之比较[J].黑龙江对外经贸,8：42-53.
[21]房振明,王春峰.2005.基于不规则数据的中国股市微观结构研究[J].系统工程学报,2：89-93.
[22]补冯林,张卫国,何伟.2005.基于超高频数据的股票流动性度量研究[J].统计与决策,2：24-26.
[23]张晖.2007.香港权证市场发展给内地的启示[J].南方金融,6：21-23.
[24]胡朝晖.2006.中国权证市场的发展路径[J].特区经济,3：35-38.
[25]马超群,张明良.2006.中国证券市场的LOG-ACD模型及其应用研究[J].统计与决策,2：43-46.
[26]毛崇峰.2004.股票市场流动性风险度量方法及其实证研究[M]：[硕士].湖南：湖南大学工商管理学院,16-24.
[27]詹场,胡星阳.2001.流动性衡量方法之综合评论[J].国家科学委员会研究汇刊：人文及社会科学(台湾),11(3)：205-221.
[28]纪路,陈伟忠.2002.市场微观结构及其对市场流动性的影响分析[J].财经问题研究,9：14-16.
[29]王晶,王玉玲,向东进等.2006.自回归条件持续期(ACD)模型研究[J].统计与决策,6：42-43.
[30]仲黎明,刘海龙,吴冲锋.2003.中国股票市场流动性：过高还是过低[J].当代经济科学,3：58-61.
[31]王晶,王玉玲,向东进.2007.自回归条件持续期(ACD)模型的统计特性分析[J].汉江大学学报,6：23-24.
[32]耿克红,张世英.2008.超高频数据下金融市场持续期序列模型述评[J].中国管理科学,8：16-20.
[33]Engle,R.F.,Russell, J. R.1998. Autoregressive conditional duration:A New model for irregularly-spaced transaction data [J].Econometrica 66, a:1127-1162.
[34]Bauwens.L.,Giot,.2000. The logarithmic ACD model:An application to the bid-ask quote process of three NYSE stocks[J].Annalesd'Economieet de Statistique,60:117-150.
[35]Lunde, A.1999. A generalized gamma autoregressive conditional duration model[C]. University of Aarhusr:1-20.
[36]Fernandes,M.,Grammig, J.2003. A Familiy of Autoregressive Conditional Duration Models[C].Graduate School of Economics.Getulio Vargas and CORE Discussion Paper:1-20.
[37]Hentschel, L.1995. All in the family:Nesting symmetric and asymmetric GARCH models [J]. Journal of Financial Economics,39:71-104.
[38]Zhang, M. Y, Russell, J. R., Tsay, R. S.2001. A nonlinear autoregressive conditional duration model with applications to financial transaction data [J].Journal of Econometrics,104:179-207.
[39]McInish T, R Wood.1992. An Analysis of Intraday Patterns in Bid/Ask Spreads for NYSE Stocks.Journal of Finance,47(2):753-764
[40]Engle R F.2000. The econometrics of ultra-high-frequency data.Econometrica, 68(1):1-22.
[41]Shleifor A.2000. In Efficient markets:An Introduction to Behavioral Finance [working paper].Oxford University:1-18.
[42]Engle R F, Jeffrey R Russell.1994. Forecasting Transaction Rates:The Autoregressive Conditional Duration Model:[working paper].Cambridge:5-40.
[43]Luc Bauwens, Pierre Giot.2000. Asymmetric ACD models:introducing price information in ACD models with a two state transition model:[discussion paper].University catholique de Louvain, Louvain-La-Neuve:1-24.
[44]Antonio Cosma, Fausto Galli.2004. A Nonparammtric ACD Model:[discussion paper].University of Lugano:1-24.
[45]Russell, Jeffrey R Engle.1998. Econometric Analysis of Discrete Valued, Irregulalry spaced Financial Transactions Data Using a New Autoregressive Conditional Multinomial Model:[working paper].University of Chicago,Graduate School of Business:1-31.
[46]Ghysels E, Gourieroux C, Jassik J.2004. Stochastic volatility duration models. Journal of Econometrics,119(2):413-433.
[47]Bauwens L, Giot P.2000. Modeling and predicting intra-day price movements in stock markets with autoregressive conditional duration Models:[working paper].Universit'e Catholique de Louvain:5-23.
[48]Yanhui Liu, Yongmiao Hong, Shouyang Wang.2005. How well can Autoregressive Duration Models Capture the Price Durations Dynamics of Foreign Exchanges.[2009-5-12].http://www.ccfr. org.cn.
[49]Lunde A.2000. A generalized gamma autoregressive conditional duration model: [Working paper].Aarlborg University:4-17.
[50]Gramming J, Maurer K O.2000. Non-monotonic hazard function and the autoregressive conditional duration model.The Econometrics Journal,3(1):16-38.
[51]Engle R F, Russel J.1997. Forecasting the frequency of changes in quoted foreign exchange prices with the autoregressive conditional duration model. Journal of Empirical Finance,4(2):187-212.
[52]Easley, O'Hara, Maureen.1992. Time and the process of security price adjustment. Journal of Finance,47(2),577-606.
[53]Rober F Engle, Joe Lange.2001. Predicting VNET:A model of the dynamics of market depth. Journal of Financial Markets,4(2):113-142.
[54]Dufour A, Engle R F.2000. Time and the price impact of a trade.Journal of Finance,55(6):2467-2498.
[55]Zumbach G O.2005. Considering time as the random variable:the first hitting time.[2009-5-18]. http://ssrn.com/abstract.