Calculating the Serial Correlation LM Test Statistics
Posted: Mon Dec 13, 2021 5:30 pm
Hello,
I am using GARCH models. However, there is no built-in Lagrange multiplier (LM) tests in EViews 11 for serial correlation in the residuals.
Below the codes I have used to conduct the LM test.
equation eq1.ls sf c blm --> This is the regression of sf on a constant and the independent variable (blm).
eq1.makeresid resid01 --> I saved the residuals of the fitted model to test whether past residuals influence the current residuals.
equation eq2.ls resid01 c blm resid01(-1) resid01(-2) --> This is the auxiliary regression of the residuals on the original regressor and lagged residuals up to 2 order.
Can anyone tell me the codes for calculating the LM test statistics, including the F-statistic and Obs*R-squared statistic? Any advice would be appreciated. I hope that my question is clear enough for anyone to answer. Please let me know if you need further information. Thank you.
I am using GARCH models. However, there is no built-in Lagrange multiplier (LM) tests in EViews 11 for serial correlation in the residuals.
Below the codes I have used to conduct the LM test.
equation eq1.ls sf c blm --> This is the regression of sf on a constant and the independent variable (blm).
eq1.makeresid resid01 --> I saved the residuals of the fitted model to test whether past residuals influence the current residuals.
equation eq2.ls resid01 c blm resid01(-1) resid01(-2) --> This is the auxiliary regression of the residuals on the original regressor and lagged residuals up to 2 order.
Can anyone tell me the codes for calculating the LM test statistics, including the F-statistic and Obs*R-squared statistic? Any advice would be appreciated. I hope that my question is clear enough for anyone to answer. Please let me know if you need further information. Thank you.