McLeod-li test

[new_user1]

How to perform Mcleod-li tets on squared residuals in SAS? Thank you

[sbxkoenk]

Are you talking about this test?

To test for heteroscedasticity, the AUTOREG procedure uses the portmanteau Q test statistics (McLeod and Li 1983), Engle’s Lagrange multiplier tests (Engle 1982), tests from Lee and King (1993), and tests from Wong and Li (1995). Test statistics and significance p-values are reported for conditional heteroscedasticity at lags 1 through 12. The Jarque-Bera normality test statistic and its significance level are also reported to test for conditional nonnormality of residuals. The following tests for independence are also supported by the AUTOREG procedure for residual analysis and diagnostic checking: Brock-Dechert-Scheinkman (BDS) test, runs test, turning point test, and the rank version of the von Neumann ratio test.

See here :

https://go.documentation.sas.com/doc/en/pgmsascdc/9.4_3.5/etsug/etsug_autoreg_overview.htm

Cheers,

Koen

[sbxkoenk]

Look at these tests :
( variety of model diagnostic information, including the following: )
◦McLeod-Li portmanteau Q test for ARCH disturbances
◦Engle’s LM test for ARCH disturbances
◦Lee and King’s for ARCH disturbances
◦Wong and Li’s test for ARCH disturbances

Examples :
SAS® 9.4 and SAS® Viya® 3.5 Programming Documentation | SAS 9.4 / Viya 3.5
SAS/ETS User's Guide
The AUTOREG Procedure
Testing for Heteroscedasticity
https://go.documentation.sas.com/doc/en/pgmsascdc/9.4_3.5/etsug/etsug_autoreg_gettingstarted11.htm

Heteroscedasticity and GARCH Models
https://go.documentation.sas.com/doc/en/pgmsascdc/9.4_3.5/etsug/etsug_autoreg_gettingstarted12.htm

Ciao,

Koen

[new_user1]

Thank you for your replies! I wasn' sure if I could use that test since it's not a regression model but I have calculated squared residuals already. Anyway, I'm not sure what my inputs would be and if I can use the test by entering already calculated values.

[sbxkoenk]

Hello,

If you have pre-calculated values already

, then I think you have to program the test in a data step or with our matrix language (SAS/IML).

If you have full doc on the test, that should be easy to do.

Cheers,

Koen