lecture9

# E adjusted for ination 15 30 e xample 220000 price of

This preview shows page 1. Sign up to view the full content.

This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: se in UK (in £) Explanatory variable: GDP (in billions of £) Time span: 1975 Q1 - 2011 Q2 All series are seasonally adjusted and in real prices (i.e. adjusted for inﬂation) 15 / 30 E XAMPLE 220000 Price of representative house 200000 180000 160000 140000 120000 100000 80000 60000 1975 1980 1985 1990 1995 2000 2005 2010 16 / 30 E XAMPLE 17 / 30 E XAMPLE We test for positive serial correlation: H0 : ρ ≤ 0 (no positive serial correlation) HA : ρ > 0 (positive serial correlation) One-sided DW critical values at 95% conﬁdence for T = 146 and k = 1 are: dL = 1.72 and dU = 1.74 Decision rule: if d < 1.72 if d > 1.74 if 1.72 ≤ d ≤ 1.74 reject H0 do not reject H0 inconclusive Since d = 0.02 < 1.72, we reject the null hypothesis of no positive serial correlation 18 / 30 A LTERNATIVE APPROACH Suppose we suspect the stochastic error term to be AR(p) εt = ρ1 εt−1 + ρ2 εt−2 + . . . + ρp εt−p + ut Since OLS is consistent even under autocorrelation, the residuals are co...
View Full Document

## This document was uploaded on 02/26/2014.

Ask a homework question - tutors are online