Under the assumption of stationarity, we can transform any autoregressive process into an infinite moving average equation. For example, yt = Øyt-1 + Et, can be written as. 1.1 Yt = & + Ø&t−1+ 2+… .= Σj=10¹&t-j This suggests that ye can be described entirely as a function of the errors (or shocks) during past and present periods of time. i) Suppose a shock (or innovation) starts at period 1 (j = 1) and ends at period 3, what will be the effect of this shock (assuming the rest remains the same). [3 Marks] Note: recall that, under the assumption of stationarity, the effect of the change in the initial shock is given by; ayt = Ø1 Əεt-j ii) From equation 1.1 above, we note that the cumulative effect of the temporal shock that starts at time j is calculated as; 1 ayt · = 1 + ز + ز + .... + Ø/ Əεt-j 1- Ø j=0 What range of values of the parameter Ø would render the time series process in question stationary? [3 Marks] Note: derivations are not required to answer this question