nag_generate_agarchII (g05hlc) generates a given number of terms of a type II AGARCH
process (see
Engle and Ng (1993)).
A type II AGARCH
process can be represented by:
Here
is the number of observations in the sequence,
is the
observed value of the GARCH
process at time
,
is the conditional variance at time
, and
the information set of all information up to time
. Symmetric GARCH
sequences are generated when
is zero, otherwise asymmetric GARCH
sequences are generated with
specifying the amount by which positive (or negative) shocks are to be enhanced.
Engle R (1982) Autoregressive conditional heteroskedasticity with estimates of the variance of United Kingdom inflation Econometrica 50 987–1008
- 1:
num – IntegerInput
-
On entry: , the number of terms in the sequence.
Constraints:
- ;
- .
- 2:
p – IntegerInput
-
On entry: the GARCH argument .
Constraint:
.
- 3:
q – IntegerInput
-
On entry: the GARCH argument .
Constraint:
.
- 4:
theta[] – const doubleInput
-
On entry: the first element contains the coefficient
, the next
q elements contain the coefficients
, for
. The remaining
p elements are the coefficients
, for
.
- 5:
gamma – doubleInput
-
On entry: the asymmetry argument for the GARCH sequence.
- 6:
ht[num] – doubleOutput
-
On exit: the conditional variances , for , for the GARCH sequence.
- 7:
et[num] – doubleOutput
-
On exit: the observations , for , for the GARCH sequence.
- 8:
fcall – Nag_Garch_Fcall_TypeInput
On entry: if
, a new sequence is to be generated, else if
a given sequence is to be continued using the information in
rvec.
- 9:
rvec[] – doubleInput/Output
-
On entry: the array contains information required to continue a sequence if .
On exit: contains information that can be used in a subsequent call of nag_generate_agarchII (g05hlc), with .
- 10:
fail – NagError *Input/Output
-
The NAG error argument (see
Section 3.6 in the Essential Introduction).
Not applicable.
None.