# Eg measurement error simultaneous equations the

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: β2 Xte + ut −1 β2 Xte = Yt −1 − β1 − ut −1 Yt = β1 λ − (1 − λ)Yt −1 + β2 λXt + ut − (1 − λ)ut −1 In equilibrium, ¯ ¯ ¯ Y = β1 λ + (1 − λ)Y + β2 λX 21 / 62 Introduction Time Series and OLS Two Dynamic Models Autocorrelation Expectations Model Partial Adjustment Model Adaptive Partial Adjustment Model Quite often, we are interested in a target value or desired value of a dependent variable. (eg. inventory...) Partial Adjustment Model The actual increase in the dependent variable Yt − Yt −1 is assumed to be proportional to the discrepancy between the desired value and the previous value. Yt − Yt −1 = λ(Yt∗ − Yt −1 ) This is another type of dynamic model: Yt∗ = β1 + β2 Xt + ut Yt − Yt −1 = λ(Yt∗ (Target ) − Yt −1 ) 22 / 62 Introduction Time Series and OLS Two Dynamic Models Autocorrelation Expectations Model Partial Adjustment Model Adaptive Combining the two equations we obtain: Yt = β1 + β2 λXt + β2 (1 − λ)Yt −1 + λut Long run effect of X? Short run? 23 / 62 Introduction Time Series and OLS Two Dynamic Models Autocorrelation Expectations Model Partial Adjustment Model Adaptive Combining the two equations we obtain: Yt = β1 + β2 λXt + β2 (1 − λ)Yt −1 + λut Long run effect of X? Short run? 24 / 62 Introduction Time Series and OLS Two Dynamic Models Autocorrelation Assumption C7 Autocorrelation Detection Lagged Dependent Assumption C7 Assumption C7 requires 2 conditions: ut is uncorrelated with Xjt ut is uncorrelated with Xjs for s = t The violation of the ﬁrst part renders OLS biased and inconsistent. (eg. measurement error, simultaneous equations,...) The violation of the second part affects unbiasedness but does not affect consistency. 25 / 62 Introduction Time Series and OLS Two Dynamic Models Autocorrelation Assumption C7 Autocorrelation Detection Lagged Dependent Assumption C7 Assumption C7 requires 2 conditions: ut is uncorrelated with Xjt ut is uncorrelated with Xjs for s = t The violation of the ﬁrst part renders OLS biased and inconsistent. (eg. measurement error, simultaneous equations,...) The violation of the second part affects unbiasedness but does not affect consistency. 26 / 62 Introduction Time Series and OLS Two Dynamic Models Autocorrelation Assumption C7 Autocorrelation Detection Lagged Dependent Assumption C7 Assumption C7 requires 2 conditions: ut is uncorrelated with Xjt ut is uncorrelated with Xjs for s = t The violation of the ﬁrst part renders OLS biased and inconsistent. (eg. measurement error, simultaneous equations,...) The violation of the second part affects unbiasedness but does not affect consistency. 27 / 62 Introduction Time Series and OLS Two Dynamic Models Autocorrelation Assumption C7 Autocorrelation Detection Lagged Dependent Autocorrelation There are two main types of autocorrelation: AR(p): ut = ρ1 ut −1 + · · · + ρp ut −p + εt MA(q): ut = εt + λ1 εt −1 + · · · + λq εt −q but we will mainly focus on the special cases AR(1): u...
View Full Document

## This document was uploaded on 03/12/2014 for the course ECON 202 at University of London University of London International Programmes (Distance Learning).

Ask a homework question - tutors are online