Bootstrpped Data Series

[msrahman]

Hello,

I generated data series using a bivariate GARCH-M model by bootstrapping. The GARCH instruction worked nicely with the original data, but is not working with bootstrapped series. If the GARCH model fits well with the original series, shouldn't it work with bootstrapped series?
I would appreciate any comment. Thanks.

S Rahman.

Here is a part of the code:

do draw=1,ndraws
boot entries bstart bend gstart gend
*
* Update the variance, post-multiply the shuffled standardized
* residuals by a square root of the variance, save the outer product
* and return the re-flated residuals.
*
gset rv bstart bend = h=hf,uboot=%decomp(h)*rvstd(entries(t)),uu=%outerxx(uboot),uboot
set ff bstart bend = t
set Y1 bstart bend = %beta(1)+ %beta(2)*Y1{1}+%beta(3)*ff+rv(t)(1)
set YF1 bstart bend = Y1
set Y2 bstart bend = %beta(4)+ %beta(5)*Y2{1}+%beta(6)*sqrt(h(t)(1,1))+%beta(7)*sqrt(h(t)(2,2))+%beta(8)*rv(t-1)(1)+%beta(9)*rv(t-2)(1)+%beta(10)*rv(t-3)(1)+rv(t)(1)
set YF2 bstart bend = Y2
end do draw
print / YF1 YF2