INTRODUCTION TO ECONOMETRICS II ECO 306 NOUN 118
UNIT 2: AUTOCORRELATION CONTENTS 4.2.1.0 Introduction
4.2.2.0
Objectives 4.2.3.0 Main Content
4.2.3.1 Possible Causes of Autocorrelation
4.2.3.2 Detection of First-Order Autocorrelation: the Durbin–Watson Test
4.2.4.0
Summary 4.2.5.0 Conclusion
4.2.6.0 Tutor-Marked Assignment
4.2.7.0 References/Further
Reading 4.2.1.0 INTRODUCTION Autocorrelation is the correlation between the error terms arising in time series data. Such correlation in the error terms often arises from the correlation of the omitted variables that the error term captures. Furthermore, the assumption in the third Gauss–
Markov condition is that the value taken by the disturbance term in any observation and determined independently of its values
in all the other observations, is satisfied, and hence that the population covariance of and is 0 for
i ≠ j. When the condition is not satisfied, the disturbance term is said to
be subject to autocorrelation, often called serial correlation or cross-autocorrelation.
4.2.2.0 OBJECTIVE The main objective of this unit is to provide a basic understanding that autocorrelation may arise as a consequence of the exclusion of a significant variable or the mathematical misspecification of regression model.
INTRODUCTION TO ECONOMETRICS II ECO 306 NOUN 119
4.2.3.0 MAIN CONTENTS The significances of autocorrelation for OLS are to some extent comparable to those of heteroscedasticity. The regression coefficients remain unbiased, but OLS is inefficient because one can find an alternative unbiased estimator with smaller variance. The other main concern, which should
not be mixed up with the first, is that the standard errors are estimated wrongly, probably being biased downwards. Finally, although in general autocorrelation does not cause OLS estimates to be biased, there is an important special case where it does.
Share with your friends: 
