MATLAB金融工具箱的应用实验报告.docx

MATLAB金融工具箱的应用实验报告 该数据选取的是TCL自2004年1月7日起至今的股票收盘价数据： 时间序列分析 x=xlsread(tcl); tcl(1,1) ans = 731979 tcl(1,2) ans = 8.3500 plot(tcl(:,1),tcl(:,2)); datetick(x,23); xlabel(Date); title(TCL Composite ); 绘制收益率序列 Return=price2ret(tcl(:,2)); Time=tcl(:,1); t=Time(2:end); plot(t,Return); datetick(x,23); 自相关 autocorr(Return) title(ACF); 偏自相关 parcorr(Return); title(PACF); AR模型 m=ar(Return,2) m = Discrete-time AR model: A(z)y(t) = e(t) A(z) = 1 - 0.03316 z^-1 + 0.01952 z^-2 Sample time: 1 seconds Parameterization: Polynomial orders: na=2 Number of free coefficients: 2 Use polydata, getpvec, getcov for parameters and their uncertainties. Status: Estimated using AR (fb/now) on Return. Fit to estimation data: 0.08195% FPE: 0.000963, MSE: 0.0009614 ARMA模型 format long gfor a=1:10 for c=1:10 m=armax(Return,na,a,nc,c); FPE(a,c)=fpe(m);FPE(a,c)=fpe(m); end end nmin=min(FPE(:))[na,nc]=find(FPE==nmin) ormat long gfor a=1:10 nmin = 0.000962185144313305 na = 1 nc = 1 结果分析：ARMA(1,1)为最合适的拟合模型。