SAS里不能直接估计GJR GARCH模型吗?

shiyiming

在proc autoreg里,能否直接估计非对称的GJR GARCH模型?

proc autoreg data=r;
model y=/ garch=(q=1,p=1,type=?);
run;

type=的选项只有exp, INTEGRATED,

shiyiming

在autoreg 里好像不行,

我查了一下, 利用model可以实现,看起来还挺复杂的!

GJR-GARCH Model
Another asymmetric GARCH process is the GJR-GARCH model of Glosten, Jagannathan and Runkle (1993). They propose modeling , where vt is i.i.d. with zero mean and unit variance, and



where It-1=1 if  and It-1=0 if ut-1<0.

You can use the following code to estimate a GJR-GARCH(1,1) model.


   /* Estimate GJR-GARCH Model */         
   proc model data = gjrgarch ;
      parms arch0 .1 arch1 .2 garch1 .75 phi .1;
      /* mean model */
      y = intercept ;
      /* variance model */
      if zlag(resid.y) > 0 then
         h.y = arch0 + arch1*xlag(resid.y**2,mse.y) + garch1*xlag(h.y,mse.y)  ;
      else
         h.y = arch0 + arch1*xlag(resid.y**2,mse.y) + garch1*xlag(h.y,mse.y) +
               phi*xlag(resid.y**2,mse.y) ;
      /* fit the model */
      fit y / method = marquardt fiml ;
   run ; quit;