0% found this document useful (0 votes)
10 views

Sample_Test_One_Solution

Uploaded by

tylgclash
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
10 views

Sample_Test_One_Solution

Uploaded by

tylgclash
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

1.

( 20 points)

(a) (8 points) What are the two conditions for stationary time series?

"Xt- l> S-/cvf i<N\o.~ ~j .


0); E¼=IU iri~rh«J ref -t

(2--) ·, (J(}i )-= [6\J (rt1+1i /Yt ) {]fl~ ~nd}, 01\ h .

(b) (12 points) Consider the time series

Xt = WtZt,
where {Wt} and { zt} are two independent white noise processes with variance
a 2 . Check whether Xt is a stationary process.

C2 J crlh )-.:~ Cov ( f'X.t:tt1, 0Ct )


=- t_ ?(w/Xt - f extt-"' E."X-r-
=- t= rx-t+h rx1:
::._ b ( LUi+h (t+-h u\Jt 2-t)
=- t: (GUltti LVL ) t (~t+1, ~-l >
-- 6 t+-1 h=<o
L O/ o+l~rGv~ .
2. (20 points) Consider the MA(l) process

Xt =Wt+ 0Wt-l·

(a) (12 points) Compute the autocovariance function for x 1

1. ./ ()t~ .}__) 62. h


O'lV\)= L () 6", / /hi:=/
0 1 O~:JQ

l.ieQ ~re. note LN2 -1-2_0.nn 0 tcited.r)Jf


Jeto.ifa'
(b) (6 points) Compute the ACF for Xt

lI h~-
()
f+l9:i.. I 1~1
0 1 ot~rwile ,

(c) (2 points) Is x 1 a linear and causal process?

. {P B:J ckJ,,J,<•, L, t lQc,r pro {9(!, _r~ wk} havQ_ 1wi


fvrW\ of !Xt .:c_ IU-+ f:., lfj Wi -j _ 5-«-l't /</JO
0<t co~ {;Q_ cLeor~ wr-dteA Ct'~ uho~ b~ 1eltL:,
IU-=-o ) Lfo ==- I I :: () 1
3. (20 points) Consider the trend stationary model

Xt = f3o + f31t + Wt,


where Wt is a white process.

(a) (10 points) Check whether 'vxt = Xi - x 1_ 1 is stationary.

[ I) k Vf'Kt - b rxt- E?X-t,


-=- fo+~11- ( ~+ f1 ct-1) )
-= @1 /,1c~c&w/ of -t-
( 2-) 'oLh y~ Cu\J ( ,7/Xt+ry I C?tX-t: )
M-
- {_,-
~ ( d / ~llt , j-
-= CJVl tx't+~ - rxt1-,d / rx-f -rxt-,)
::::. C{J\) (_ f,
-t-lVt-H,- ~i-1, Wt-Lvt-1)1,+
-== cw Luvt+h, W+ > - Cov(lvt+ii , (,,Vt-, )-C<JvC(;Vt ,A,,
(b) (10 points) Let B be the back-shift operator. 'Express (1-B)2xi using the time fhi, v \ff;)
series w,,, f3o, f31 and t. fC,SV( LV-Hh-1,
2 6 ).. h=-o lVt-1 )
)
l~I
o/ ot luU'lv~

(J- B) 2
rxt ul- 2g i- /?/-JX,t-
- rxt -2rx-t-, t rx-&-2.
- ..t~ t-t-~\Jt, - 2(fi>t~, {;t~),-t~vt-1)f ?ot~ili-i)-H4-l
1

W+ - lGVt-1 -t Gv t-2. .

You might also like