Page 198 - Special Topic Session (STS) - Volume 1
P. 198
STS425 Arifah B. et al.
t
Var [B t H B s H ] s 2H . (3)
The relation in Equation (3) defines its covariance structure as follows:
1 2H 2H 2H
Cov (B H , B H ) (t s t s ), (4)
s
t
2
Thus, for H 1 , the fOU process is Gaussian and ergodic but it is neither
2
1
Semimartingal nor Markovian. For H , the fOU process shows a long
2
memory property. From Equation(2) we get:
t
Y y e t e (t s ) dB s H , t 0, X x 0 . (5)
t
0
0
0
Let y 0 L 0 ( ), and , 0. Then for all s the
a
integration a t e dB s H , t , a exist as a Riemann-Stieltjes pathwise integral
s
which is continuous in t, and the unique almost surely continuous solution
of Equation (5) is
s
Z t H , 0 y e t (y 0 0 t e dB s H ), t 0, (6)
Particularly, the restriction to t 0 of the following almost surely
continuous process
,
H
Z 0 t e (t s ) dB s H , t R (7)
t
which can solve Equation (5) with initial condition y Z 0 H . The Gaussian
0
process (Z t H ) tR is stationary since it follows the stationarity of the
increments of {B t H }. Additionally, for each initial condition y 0 L 0 ( ) ,
Z Z t H ,x 0 e t (Z y 0 ) 0, as t . (8)
H
H
0
t
This implies that every stationary solution of Equation (5) has the same
distribution as (Z t H ) . The (Z t H ,x 0 ) t 0 is defined as a FOU process with
t
0
initial condition y and (Z t H ) tR is the stationary FOU process that is
0
1
ergodic and for H it exhibits as long range dependence. Since the
2
values of H and can be estimated without having the value, then
the estimation for the unknown parameter ( , , )H will be carried
out in several steps. The covariance theorem of the fOU is shown in Chen
et al. (2017).
187 | I S I W S C 2 0 1 9