STAT317 16S1 ECON323 16S1 Paper Title: Time Series Methods

Time Series 时间序列代写 / CS代考

University of Canterbury
Mid-year Examinations 2016
Prescription Number(s): STAT317-16S1 / ECON323-16S1 Paper Title: Time Series Methods
Assignment Project Exam Help https://tutorcs.com
Time Allowed: 2 hours
Number of Pages: 3
WeChat: cstutorcs
Instructions for candidate:
 This is a restricted examination
 Only stickered calculators permitted
 Remember to write your name and student
number on all answer booklets/pages  Start each question on a new page
 All questions are equally worth
 Show all working
CS Help, Email: tutorcs@163.com
QUESTIONS START ON PAGE 3
Assignment Project Exam Help https://tutorcs.com WeChat: cstutorcs
2 STAT317-16S1/ECON323-16S1

Code Help, Add WeChat: cstutorcs
QUESTION 1
What are the invertibility and stationarity conditions for an ARMA process? Explain the reasons and the importance for such conditions.
QUESTION 2
QUESTION 5

Home


Given the moving average process:
x z 0.7z 0.5z z ~N(0,2),
t t t1 t2 t
Find the values  ( k ) of the autocorrelation function for k=1,2,3.
QUESTION 4
Illustrate the major steps of the classical decomposition of a time series.
3 STAT317-16S1/ECON323-16S1
QUESTION 3
Identify the order of the following ARMA(p,q) models and determine whether they are causal and/or invertible:
xt  0.8xt1  0.15 xt2  zt  0.3zt1 ; xt  xt1  0.5xt2  zt  zt1 ;
~ N (0, 2 ) . Please show all your workings. Assignment Project Exam Help
Explain why differencing a time series you remove a deterministic trend and why you
QUESTION 6
Show that an invertible MA(k) model for any integer value of k is equivalent to an AR of infinite order and that a causal AR(k) model for any integer value of k is equivalent to a MA of infinite order.
should not difference more than twice.
WeChat: cstutorcs
END OF PAPER

Code Help