Autor: Mendoza Hernandez Mayolo Omar
\[ Y_t=5+e_t-{\frac12}e_{t-1}+{\frac14e_{t-2}} \\ E[Y_t]=0 \\ Var(Y_t)=Var(5+e_t-{\frac12}e_{t-1}+{\frac14e_{t-2}}) \\ Var(Y_t)=Var[1+{\frac14}+{1/16}]\sigma_e^2 \\ Cov(Y_pY_{t-1})=Cov(e_t-{\frac12}e_{t-1}+{\frac14e_{t-2}},e_{t-1}-\frac12e_{t-2}+\frac14e_{t-3}) \\ Cov(Y_pY_{t-1})=Cov(-{\frac12}e_{t-1}+{\frac14e_{t-2}},e_{t-1}-\frac12e_{t-2}) \\ Cov(Y_pY_{t-1})=Cov(-{\frac12}e_{t-1},e_{t-1})+Cov(\frac14e_{t-2},-\frac12e_{t-2}) \\ Cov[-\frac18-\frac12]\sigma^2_e=\frac58\sigma^2_e \\ Cov(Y_pY_{t-2})=Cov(e_t-{\frac12}e_{t-1}+{\frac14e_{t-2}},e_{t-2}-\frac12e_{t-3}+\frac14e_{t-4}) \\ Cov(\frac14e_{t-2},e_{t-2})=\frac14\sigma^2_e \]
ARMAacf(ma=list(-0.5,-0.4))
## 0 1 2 3
## 1.0000000 -0.2127660 -0.2836879 0.0000000
ARMAacf(ma=list(1,0.6))
## 0 1 2 3
## 1.0000000 0.6779661 0.2542373 0.0000000
ARMAacf(ma=list(1,0.6))
## 0 1 2 3
## 1.0000000 0.6779661 0.2542373 0.0000000
$$ -/1+()^2=
$$
ACF=ARMAacf(ar=0.6,lag.max=8)
plot(y=ACF[-1],x=1:8,xlab='Lag',ylab='ACF',type='h') ; abline(h=0)
ACF=ARMAacf(ar= -0.6,lag.max= 8)
plot(y=ACF[-1],x=1:8,xlab='Lag',ylab='ACF',type='h',ylim=c(-1,1)) ; abline(h=0)
ACF=ARMAacf(ar=0.95,lag.max=20)
plot(y=ACF[-1], x=1:20, xlab='Lag', ylab='ACF', type='h', ylim=c(0,1)) ; abline(h=0)
ACF=ARMAacf(ar=0.3,lag.max=20)
plot(y=ACF[-1], x=1:20, xlab='Lag', ylab='ACF', type='h', ylim=c(0,1)) ; abline(h=0)
a)MA(1): correlación entre -0.5 y 0.5 b)MA(2): correlacion distinta a cero en los primeros 2 c)AR(1): d)AR(2): e)ARMA(1,1): tiene autocorrelacion en descomposicion exponencial a partir del retraso 1, sin embargo, no lo tienen en el retraso cero.
ACF=ARMAacf(ar=0.7, ma=0.4, lag.max = 20)
plot(y= ACF[-1], x=1:20, xlab="lag", ylab="ACF", type = "h"); abline(h=0)
ACF=ARMAacf(ar=0.7, ma=-0.4, lag.max = 20)
plot(y= ACF[-1], x=1:20, xlab="lag", ylab="ACF", type = "h"); abline(h=0)
ARMAacf(ma=c(1,-6))
## 0 1 2 3
## 1.0000000 -0.1315789 -0.1578947 0.0000000
ARMAacf(ma=c(-1/6,-1/6))
## 0 1 2 3
## 1.0000000 -0.1315789 -0.1578947 0.0000000
Todas las raices de los polinomios son recíprocas entre sí. Sólo el MA(2)cuando \[ \theta_1=\theta_2=-\frac{1}{6} \] es invertible
ARMAacf(ma=c(-0.5,0.25,-0.125,0.0625,-0.03125,0.015625))
## 0 1 2 3 4 5
## 1.00000000 -0.49990844 0.24977110 -0.12451932 0.06152719 -0.02929866
## 6 7
## 0.01171947 0.00000000