i i 1 
0.00 75.00 
150.00 225.00 300.00 375.00 450.00 525.00 600.00 
>t 
5.00 4 
4 
2.504 
me | 
4 
-5.00 
100 150 200 250 
ot 
Fig. 5.10. Simulated AR(1) process 
X,-0.5 Xey =€Er, Er: N[O, 1]. 
A1.2; pp. 251, 252, and 253. Heree€, is a pure random Gaussian process N[0, 1], and the 
same process, which was generated as a pure random process AR(0) in Fig. 5.3, was 
used. Figure 5.11a shows the theoretical autocorrelation coefficient @(r) = R(r)/R(0), 
from Eqs. 5.36 and 5.37 using the designed value of 0? = 1 anda = —0.5. Figure 5.11b is 
the estimated autocorrelation function 6(r) = Rr) /R(0) from the simulated process in Fig. 
5.10. An AR model was fitted to this process, and the order actually obtained was 1 by 
113 
