0% found this document useful (0 votes)
6 views48 pages

Serial Correlation

Serial correlation occurs when the error terms in a regression model are correlated, violating classical assumptions. It can be first-order, where the current error term is influenced by the previous one, and can be positive or negative based on the sign of the autocorrelation coefficient ρ. Detection methods include the Durbin-Watson statistic and LM test, while removal techniques involve autoregressive conversion and first differencing.

Uploaded by

yasir6028
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
6 views48 pages

Serial Correlation

Serial correlation occurs when the error terms in a regression model are correlated, violating classical assumptions. It can be first-order, where the current error term is influenced by the previous one, and can be positive or negative based on the sign of the autocorrelation coefficient ρ. Detection methods include the Durbin-Watson statistic and LM test, while removal techniques involve autoregressive conversion and first differencing.

Uploaded by

yasir6028
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 48

Serial Correlation

1
Serial Correlation

• Serial correlation occurs when Classical Assumption, which


assumes uncorrelated observations of the error term, is
violated (in a correctly specified equation!)
• The most commonly assumed kind of serial correlation is first-
order serial correlation, in which the current value of the error
term is a function of the previous value of the error term:
εt = ρεt–1 + ut

where: ε = the error term of the equation in question


ρ = the first-order autocorrelation coefficient
u = a classical (not serially correlated) error term

2
Serial Correlation (cont.)

• The magnitude of ρ indicates the strength of the serial


correlation:
– If ρ is zero, there is no serial correlation
– As ρ approaches one in absolute value, the previous observation
of the error term becomes more important in determining the
current value of εt and a high degree of serial correlation exists
– For ρ to exceed one is unreasonable, since the error term
effectively would “explode”

• As a result of this, we can state that:


–1 < ρ < +1

3
Serial Correlation (cont.)

• The sign of ρ indicates the nature of the serial correlation in


an equation:
• Positive:
– implies that the error term tends to have the same sign from one
time period to the next
– this is called positive serial correlation
• Negative:
– implies that the error term has a tendency to switch signs from
negative to positive and back again in consecutive observations
– this is called negative serial correlation
• Following Figures illustrate several different scenarios

4
Positive Serial Correlation

5
No Serial Correlation

6
Negative Serial Correlation

7
Serial Correlation

• Serial correlation is usually caused by a specification error such as:


– an omitted variable and/or
– an incorrect functional form

• How does this happen?


• As an example, suppose that the true equation is:

where εt is a classical error term. If X2 is accidentally omitted from the


equation (or if data for X2 are unavailable), then:

• The error term is therefore not a classical error term

8
Serial Correlation (cont.)

• Instead, the error term is also a function of one of the


explanatory variables, X2
• As a result, the new error term, ε * , can be serially correlated
even if the true error term ε, is not
• In particular, the new error term will tend to be serially
correlated when:
1. X2 itself is serially correlated (this is quite likely in a time
series) and
2. the size of ε is small compared to the size of

9
The Consequences of Serial
Correlation
• The existence of serial correlation in the error term of an equation
violates Classical Assumption, and the estimation of the equation with
OLS has at least three consequences:
1. Serial correlation does not cause bias in the coefficient estimates
2. Serial correlation causes OLS to no longer be the minimum variance
estimator (of all the linear unbiased estimators)
3. Serial correlation causes the OLS estimates of the SE to be biased,
leading to unreliable hypothesis testing. Typically the bias in the SE
estimate is negative, meaning that OLS underestimates the standard
errors of the coefficients (and thus overestimates the t-scores)

10
Eviews: Serial Correlation
Test
• File Name: how to detect serial correlation
 Durbin Watson Statistics
 A number that tests for autocorrelation in the residuals from a statistical
regression analysis.
 The Durbin-Watson statistic is always between 0 and 4.
 A value of 2 means that there is no autocorrelation in the sample.
 Values approaching 0 indicate positive autocorrelation and values toward 4
indicate negative autocorrelation.
 We cannot use more than one lag in our model which means Durbin Watson
Statistics is not suitable for autoregressive models.
 LM test statistics or Q statistics
 We can use number of lags.

11
Eviews: Serial Correlation
Test
• File Name: how to detect serial correlation
 LM test statistics

12
Eviews: Serial Correlation
Test
• File Name: how to detect serial correlation
 LM test statistics

13
Eviews: Serial Correlation
Test
• File Name: how to detect serial correlation
 LM test statistics

14
Eviews: Serial Correlation
Test
• File Name: how to detect serial correlation
 LM test statistics

15
Eviews: Serial Correlation
Test
• File Name: how to detect serial correlation
 LM test statistics

H0: No serial correlation


HA: Serial correlation

16
Eviews: Serial Correlation
Test
• File Name: how to detect serial correlation
 LM test statistics

17
Eviews: Serial Correlation
Test
• File Name: how to detect serial correlation
 LM test statistics

18
Eviews: Serial Correlation
Test
• File Name: how to detect serial correlation
 LM test statistics

19
Eviews: Serial Correlation
Test
• File Name: how to detect serial correlation
 LM test statistics

20
Eviews: Serial Correlation
Test
• File Name: how to detect serial correlation
 Q statistics

21
Eviews: Serial Correlation
Test
• File Name: how to detect serial correlation
 Q statistics

22
Eviews: Serial Correlation
Test
• File Name: how to detect serial correlation
 Q statistics

23
Eviews: Serial Correlation
Test
• File Name: how to detect serial correlation
 Q statistics

H0: No serial correlation


HA: Serial correlation

24
Eviews: Serial Correlation
Test
• File Name: how to detect serial correlation
 Q statistics

25
Removal of Serial Correlation

• We can remove serial correlation by using following methods:


 Autoregressive (AR) conversion
• Convert the simple model into autoregressive AR model.
 First differenced method
• Convert all the variables into first differenced
• Then run regression model through the origin (no intercept)

26
Removal of Serial Correlation

• File Name: removal of autocorrelation (by taking lag)


 Autoregressive (AR) conversion

27
Removal of Serial Correlation

• File Name: removal of autocorrelation (by taking lag)


 Autoregressive (AR) conversion

28
Removal of Serial Correlation

• File Name: removal of autocorrelation (by taking lag)


 Autoregressive (AR) conversion

29
Removal of Serial Correlation

• File Name: removal of autocorrelation (by taking lag)


 Autoregressive (AR) conversion

30
Removal of Serial Correlation

• File Name: removal of autocorrelation (by taking lag)


 Autoregressive (AR) conversion

H0: No serial correlation


HA: Serial correlation

31
Removal of Serial Correlation

• File Name: removal of autocorrelation (by taking lag)


 Autoregressive (AR) conversion

32
Removal of Serial Correlation

• File Name: removal of autocorrelation (by taking lag)


 Autoregressive (AR) conversion

33
Removal of Serial Correlation

• File Name: removal of autocorrelation (by taking lag)


 Autoregressive (AR) conversion

34
Removal of Serial Correlation

• File Name: removal of autocorrelation (by taking lag)


 Autoregressive (AR) conversion

35
Removal of Serial Correlation

• File Name: removal of autocorrelation (by taking lag)


 Autoregressive (AR) conversion

H0: No serial correlation


HA: Serial correlation

36
Removal of Serial Correlation

• File Name: removal of autocorrelation (by taking lag)


 Autoregressive (AR) conversion

37
Removal of Serial Correlation

• File Name: Removal of autocorrelation (by differencing)


 First differenced method

38
Removal of Serial Correlation

• File Name: Removal of autocorrelation (by differencing)


 First differenced method

39
Removal of Serial Correlation

• File Name: Removal of autocorrelation (by differencing)


 First differenced method

40
Removal of Serial Correlation

• File Name: Removal of autocorrelation (by differencing)


 First differenced method

41
Removal of Serial Correlation

• File Name: Removal of autocorrelation (by differencing)


 First differenced method

H0: No serial correlation


HA: Serial correlation

42
Removal of Serial Correlation

• File Name: Removal of autocorrelation (by differencing)


 First differenced method

43
Removal of Serial Correlation

• File Name: Removal of autocorrelation (by differencing)


 First differenced method

44
Removal of Serial Correlation

• File Name: Removal of autocorrelation (by differencing)


 First differenced method

45
Removal of Serial Correlation

• File Name: Removal of autocorrelation (by differencing)


 First differenced method

46
Removal of Serial Correlation

• File Name: Removal of autocorrelation (by differencing)


 First differenced method

H0: No serial correlation


HA: Serial correlation

47
Removal of Serial Correlation

• File Name: Removal of autocorrelation (by differencing)


 First differenced method

48

You might also like