Skip to main content
Cross Validated

Return to Question

Post Closed as "Duplicate" by Richard Hardy, COOLSerdash, user82102, gung - Reinstate Monica, whuber♦
added 68 characters in body; edited tags; edited title
Source Link
Richard Hardy
Richard Hardy
  • 69.5k
  • 13
  • 126
  • 278

How can i deal with the serial autocorrelation of theI handle autocorrelated residuals and the Breusch-Godfrey test?

In thisthe Breusch-Godfrey test, when we refuseuse a model

$$ e_t = \varepsilon_t + \beta_1 \varepsilon_{t-1} + \dots+ \beta_p \varepsilon_{t-p}. $$

If we reject the null hypotesis for theof no serial auotocorrelation of the error, such as:

$e_t = \varepsilon_t + \beta_1 \varepsilon_{t-1} + \dots+ \beta_p \varepsilon_{t-p} $;

it means that the residuals follow an auto-regressive model of order (p$p$).

If iI want to avoid this problem, iI must add a certain number of lags of the response variable $y$ as regressors in the original model. However, but in some casecases this method is not useful. Is

Are there other options to consider?

How can i deal with the serial autocorrelation of the residuals and the Breusch-Godfrey test?

In this test, when we refuse the null hypotesis for the serial auotocorrelation of the error, such as:

$e_t = \varepsilon_t + \beta_1 \varepsilon_{t-1} + \dots+ \beta_p \varepsilon_{t-p} $;

it means that the residuals follow an auto-regressive model of order (p).

If i want to avoid this problem, i must add a certain number of lags of the response variable $y$, but in some case this method is not useful. Is there other options to consider?

How can I handle autocorrelated residuals?

In the Breusch-Godfrey test we use a model

$$ e_t = \varepsilon_t + \beta_1 \varepsilon_{t-1} + \dots+ \beta_p \varepsilon_{t-p}. $$

If we reject the null hypotesis of no serial auotocorrelation of the error, it means that the residuals follow an auto-regressive model of order ($p$).

If I want to avoid this problem, I must add a certain number of lags of the response variable $y$ as regressors in the original model. However, in some cases this method is not useful.

Are there other options to consider?

Source Link
Enzo D'Innocenzo
Enzo D'Innocenzo
  • 128
  • 1
  • 10

How can i deal with the serial autocorrelation of the residuals and the Breusch-Godfrey test?

In this test, when we refuse the null hypotesis for the serial auotocorrelation of the error, such as:

$e_t = \varepsilon_t + \beta_1 \varepsilon_{t-1} + \dots+ \beta_p \varepsilon_{t-p} $;

it means that the residuals follow an auto-regressive model of order (p).

If i want to avoid this problem, i must add a certain number of lags of the response variable $y$, but in some case this method is not useful. Is there other options to consider?