Covariance / Stationary time series

501 Views Asked by At

Evaluate the mean and covariance function for each of the following processes. In each case, determine whether or not the process is stationary.

a) $Y_t$ = $\theta_0$ +t$e_t$

b) $W_t$ = $\nabla$$Y_t$ where $Y_t$ is given in part a).

c) $Y_t$=$e_t$*$e_{t-1}$

for part a)

E[$Y_t$]=E[$\theta_0$ +t$e_t$] = $\theta_0$+tE[$e_t$]=$\theta_0$ (due to 0 mean)

then Covariance = E[$Y_t$$Y_s$]-E[$Y_t$]E[$Y_s$]

where E[$Y_t$$Y_s$]=E[($\theta_0$ +t$e_t$)($\theta_0$ +s$e_s$)]=$\theta_0^2$+$\theta_0$sE[$e_s$]+$\theta_0$tE[$e_t$]+$ts^2$ E[$e_t$$e_s$] = $\theta_0^2$

This would mean that Covariance = $\theta_0^2$ - $\theta_0$$\theta_0$=0??