【正文】
參考文獻(xiàn)Bollerslev, Tim, “Generalized Autoregressive Conditional Heteroskedasticity,” Journal of Econometrics, 1986,31, .Bollerslev, Tim, Robert F. Engle, and Daniel B. Nelson, “ARCH Models,” The Handbook of Econometrics, 1993,Volume 4.Craig , “Good Bad News and GARCH Effects in Stock Return Data,” Journal of Applied Economics ,1999,Vol IV, NO 2, 313327.Engel, Robert F, “Autoregressive Conditional Heteroskedasticity with Estimates of the Variance of UK inflation,”Econometrica,1982,50,pp,9871008.Fama , “the Behavior of Stock Market Prices,” Journal of Business, 1965,38,.Lamourenx, Christopher and William D,Lastrapes, “Heteroskedasticity in Stock Return Data:Volume versus Garch Effects,” Journal of Finance, 1990,45:221229.Peker K. Clark, “A Subordinated Stochastic Process Model with Finite Variance For Speculative Prices, ” Econometrica 1973, .Tauchen ., , “The Price variabilityvolume relationship on speculative markets,” Econometrica, 1983, 51, No,2: 485506.Torben G. Andersen. “ Return Volatility and Trading Volume: An Information Flow Interpretation of Stochastic Volatility, ”Journal of Finance,1996,7(1):169204.唐齊鳴、陳健, “市場信息流與股票波動(dòng)性分析”,經(jīng)濟(jì)管理,2001(20):5764.朱永安、石禮英,“基于混合分布假說的股市價(jià)量關(guān)系研究”,集美大學(xué)學(xué)報(bào)(哲學(xué)社會(huì)科學(xué)版),2003(9) 第6卷 第3期.9 / 9。本文提出的基于高頻數(shù)據(jù)的分類信息混合分布GARCH模型,綜合了上述模型的可取之處,并結(jié)合金融市場的微觀基礎(chǔ),以高頻數(shù)據(jù)作為基礎(chǔ)研究對象來考察分類信息(好消息和壞消息)對波動(dòng)的影響。四、結(jié) 論在研究市場信息流的模型中,其中經(jīng)典的Lamoureux和Lastrapes(1990)的模型和Torben G. Andersen (1996) 的修正的混合分布模型(MMM)雖然成功的將成交量作為信息流的代理對波動(dòng)進(jìn)行估計(jì),但沒有區(qū)分分類信息(好信息和壞信息)對波動(dòng)的影響。而且,數(shù)據(jù)表明,上證指數(shù)中由好消息帶來的成交量對波動(dòng)的影響都要小于由壞消息帶來的成交量對波動(dòng)的影響。3. 在模型(2)中,我們發(fā)現(xiàn)不管是由好消息帶來的成交量(包括平穩(wěn)的交易量和非預(yù)期的成交量)或是由壞消息帶來的成交量的系數(shù)都大于零。表1 上證指數(shù)各類模型的估計(jì)結(jié)果:上證指數(shù)