This preview shows pages 1–3. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Ec 178 ECON & BUS FORECASTING Foster, UCSD HW #3  ANSWER SHEET How would you describe the nonstationarity? How could you transform y t into a stationary series? Do you recommend deterministic models here? Explain. [8] Nonconstant mean (upward trend); possibly a random walk with positive drift; variance seems relatively constant. Try first differences or take residuals from linear trend curve. Deterministic curve fitting might be ok if there is some longrun equilibrium process associated with the variable. It is hard to tell. What is associated with this pattern in the ACF? [2] It dies out very slowly, so it indicates a random walk (unit root), a series that is not stationary. ______/ 75 50 100 150 200 Yt 20 40 60 80 100 t t = 1... 100 Figure 1  Raw Data1.000.50 0.00 0.50 1.00 Autocorrelations of y 2 4 6 8 10 Lag Bartlett's formula for MA(q) 95% confidence bands Ec 178 HOMEWORK #3 KEY p. 2 Record your test statistic and the 5% critical value in Table A. What are the null and alternative hypotheses for this test? What is your conclusion...
View
Full
Document
This note was uploaded on 06/20/2008 for the course ECON 178 taught by Professor Foster during the Spring '08 term at UCSD.
 Spring '08
 Foster

Click to edit the document details