BMAN71122: Time Series Econometrics Review Questions: II
Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: daixieit
BMAN71122: Time Series Econometrics
Review Questions: II
1 ARMA models
1. Show that the two MA(1) processes:
Xt = Zt +
Zt - 1 ; Zt ~ WN ╱0;
2、
Yt = Z~t +
Z~t - 1 ; Z~t ~ WN ╱0;
2
2、;
where 0 < |
| < 1, have the same autocovariance function.
2. Let {Yt } be an AR(1) plus noise time series defined by:
Yt = Xt + Wt ;
where Wt ~ WN ╱0;
W(2)、and {Xt } is the AR(1) process:
Xt =
Xt - 1 + Zt ; Zt ~ WN ╱0;
Z(2)、;
and 匝 [Zt Ws] = 0 for all s and t.
● Show that {Yt } is stationary and find its autocovariance function.
● Show that the time series {Ut = Yt 一
Yt - 1 } is 1-correlated.
● Conclude that {Yt } is an ARMA(1,1) process and express the three parameters of this model in terms of
,
W(2) and
Z(2) .
3. Consider an ARMA(1,1) model defined by the equations:
Xt =
Xt - 1 +
Zt - 1 + Zt ;
where {Zt } ~ WN ╱0;
2、and |
| < 1.
● Define
t =
Zt - 1 + Zt and show that
o
Xt =
j
t -j :
j=0
● Obtain an MA(&) representation:
o
Xt = j Zt -j ;
j=0
where 0 = 1 and j =
j - 1 (
+
) for j ≥ 1.
● Show that 匝 [Xt] = 0 for all t.
● Show that
X (0) =
2 1 +
+
(
+
)
● Show that for h ≥ 1,
9X (h) = 62 (φ +1(u))(一
φh - 1.
4. Let {Zt } ~ WN ╱0﹐ 62、. Check whether the following equations define stationary processes:
● Ⅹt = 0.3Ⅹt - 1 一 0.4Ⅹt -2 + Zt
● Ⅹt = 1.6Ⅹt - 1 一 0.65Ⅹt -2 + 0.05Ⅹt -3 Zt
● Ⅹt = 2Ⅹt - 1 一 5Ⅹt -2 一 2Zt - 1 + Zt
2023-05-18