2
$\begingroup$

Fitting an ARMA-GARCH model, I checked the Weighted Ljung-Box test on standardized residuals and squared residuals to verify if the model is adeguate in describing the linear dependence in the return and volatility series. Combining different orders of the ARCH and GARCH part, for example a GARCH(1,1), GARCH(2,1), GARCH(2,2),

I always get that $p$-value of the test is below 0.05 for the standardized residuals and above 0.05 for the squared standardized residuals. So that seems contrasting to me, and I don't know what type of conclusion I can make. Given the results of the test for the squared standardized residuals, I would say that the model fits well the data, but the test on the standardized residuals suggests me the opposite.

What should I do? Can I priviledge the test result on the squared standardized residuals? Should I try with higher order of the model?

In all the attempts mentioned in the post, changing only the orders of the GARCH model, I always kept fixed the ARMA model. I just tried to change the ARMA order and it looks better. The best choise seems an GARCH(2,2) without the ARMA part. This is happening assuming that innovations follow a Skew Student-$t$ distribution.

Using just a GARCH model without the mean specification seems better in terms of the Ljung-Box test on residuals, and a GARCH(1,1) model fits well the data. At the same time, adding a mean specification improves the AIC and BIC values but requests me to use a GARCH model of higher order. What should I prefer between the two specification?

$\endgroup$
  • $\begingroup$ I doubt the test has the null distribution it is supposed to have when applied to either standardized or squared standardized residuals. I have let the package author know about that before, but so far nothing has been changed. $\endgroup$ – Richard Hardy Mar 19 '16 at 15:24
  • $\begingroup$ I'm using the ugarch package in R, the data are returns of the SP500 from 1996-01-03 to 2016-02-25. $\endgroup$ – Alessandro Mar 19 '16 at 15:37
2
$\begingroup$

So that seems contrasting to me, and I don't know what type of conclusion I can make. Given the results of the test for the Square standarized residuals I would say that the model fits well the data, but the test on the standarized residuals suggest me the opposite.

You are testing two different hypotheses that are not closely related. The Ljung-Box test on (levels of) standardized residuals evaluates the dependence of the first moments with a time lag. The Ljung-Box test on squares of standardized residuals and the ARCH-LM test (on levels of standardized residuals) evaluate the dependence of the second moments with a time lag. You should not be confused that one is rejected while another is not. For example, would you get confused if you could not reject non-autocorrelation but rejected normality? Perhaps not, because these are two different things. The same applies to your case.

The findings by the Ljung-Box test on squares of standardized residuals and the ARCH-LM test are conflicting, which is unpleasant but can happen. Perhaps the dependence is borderline-strong (borderline-weak) so that one test finds it significant while the other finds it not significant.

(Also note that the tests may not be applicable to standardized residuals from a GARCH model due to nonstandard null distributions and the resulting $p$-values; ARCH-LM test is not applicable for sure and Li-Mak test should be used instead; both Ljung-Box tests may or may not be applicable, their validity does not seem trivial to me.)

Can I priviledge the test result on the squared standarized residuals?

No, you can't, because the two tests are addressing different issues.

Should I try with higher order of the model?

You may change the lag order (either ARMA or GARCH or both) or the error distribution, or even the model (try another flavour of GARCH). It is hard to tell which one is causing the trouble as their effects interact.

Using just a GARCH model without the mean specification seems better in terms of the Ljung-Box test on residuals, and a GARCH(1,1) model fits well the data. At the same time adding a mean specification improve the AIC, BIC criterion but requests me to use a GARCH model of higher order. What should I prefer between the two specification?

If you goal is to build a model for forecasting, follow AIC. Specification tests may indicate that the model is not perfect but perhaps the imperfection is small relative to the gain in forecasting accuracy due to using that particular model relative to its competitors.

$\endgroup$
  • $\begingroup$ So, the Ljung-Box test on the standarized residuals gives evidence of serial autocorrelation, while the same test applied to the squared standarized residuals suggest conditional eteroskedasticity in the standarized residual series. Is that right? $\endgroup$ – Alessandro Mar 19 '16 at 17:47
  • $\begingroup$ I would like to ask you what type of conclusions follow these results: 1) Ljung-Box test on standarized residuals suggests to accept the null hypothesis. 2) Ljung-Box test on squared standarized residuals suggests to reject the null hypotesis. 3) Arch-LM test suggests to accept the null hypothesis. Could you explain me what every test tell me? thank you very much $\endgroup$ – Alessandro Mar 19 '16 at 18:25
  • 1
    $\begingroup$ Sorry for the delay. GARCH model assumes that standardized residuals are $i.i.d.$, hence no autocorrelation and no [remaining] ARCH effects. Now the answers to your three questions: (1) You cannot reject "No autocorrelation", which is a good property to have and characterizes the conditional mean. (2) You reject "No remaining ARCH effects", hence you violate the model assumption; you have a problem with the conditional variance. (3) You cannot reject "No remaining ARCH effects". So (2) and (3) test for the same but give different results. Well, it's unpleasant but sometimes that happens. $\endgroup$ – Richard Hardy Mar 20 '16 at 3:33
  • 1
    $\begingroup$ However, the regular null distribution of the ARCH-LM test is not applicable to standardized residuals, hence you cannot trust the $p$-values in the output; you should use Li-Mak instead. I also doubt the other two tests -- Ljung-Box on standardized residuals and Ljung-Box on squared standardized residuals -- have their regular null distributions and hence correct $p$-values (although I do not have a formal proof -- but I doubt there exists a proof that they are correct). So you should take these results with a grain of salt. The fact that they are included as standard output in an R package.. $\endgroup$ – Richard Hardy Mar 20 '16 at 3:36
  • $\begingroup$ ...is not a good enough excuse. Regarding your first comment, yes, you are right. $\endgroup$ – Richard Hardy Mar 20 '16 at 3:38

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.