2
$\begingroup$

I am estimating a GJR-GARCH(1,1) model with variance targeting in R. As data I am using returns on some stock indices. While calculating the GARCH models I obtain $\alpha=0$ for some indices. From what I understand this means that volatility is constant. The code I am using for GJR-GARCH estimation is as follows and is based on the rugarch package:

garch.spec <- ugarchspec(
    variance.model = list(model="gjrGARCH", 
                          garchOrder=c(1,1), 
                          variance.targeting=TRUE), 
    mean.model = list(armaOrder=c(0,0)))
garch.fit <- ugarchfit(
    spec=garch.spec, 
    data=data, 
    solver="nlminb", 
    solver.control=list(trace=0))

And an example of my results:

           mu        alpha1         beta1        gamma1         omega 
-0.0057893647  0.0000000000  0.8666747910  0.1641368776  0.0002181445

Could you please give some advice whether such results are plausible or should I be worried? Of course I can provide the data that causes problems. And obviously I am running univariate estimations so I am taking only one series of index returns at a time.

edit: using a different solver algorithm I was able to obtain different results, however, $\alpha$ still seems to be extremely low for this model.

      mu       alpha1        beta1       gamma1        omega 
3.432135e-04 8.508012e-08 8.607153e-01 2.113815e-01 1.727337e-05 

What is the reasoning behind such low values of $\alpha$, since I am obtaining very similar results in R and in Matlab, so I doubt there is a mistake in the coefficient estimation.

$\endgroup$

1 Answer 1

3
$\begingroup$

$\alpha=0$ does not imply constant volatility. Consider just a simple Garch(1,1):

$$\sigma^2_t = \omega + \alpha \eta_t^2 + \beta \sigma^2_{t-1}$$

Note that:

$$\sigma^2_t = \omega + (\alpha + \beta) \eta_t^2 - \beta (\eta_t^2- \sigma^2_{t-1})$$

Now add $\eta_{t+1}^2$ to both sides:

$$\eta_{t+1}^2 = \omega + (\alpha + \beta) \eta_t^2 - \beta (\eta_t^2- \sigma^2_{t-1}) + (\eta_{t+1}^2 - \sigma^2_t).$$

So this is an ARMA(1,1) for $\eta_{t+1}^2$ with shocks: $\eta_{t+1}^2 - \sigma^2_t$.

So even if $\alpha=0$ volatility is not constant.

$\endgroup$
6
  • $\begingroup$ I understand your point and I was basing the constant volatility statement on a presentation I read online. But can you tell me whether such a result in case of index returns is plausible or have some consequences? I have not encountered such a result before and I'm a little lost . $\endgroup$
    – Masher
    Dec 28, 2015 at 2:30
  • $\begingroup$ Can you provide the link for that presentation? $\endgroup$
    – phdstudent
    Dec 28, 2015 at 12:22
  • $\begingroup$ The presentation can be found here: halweb.uc3m.es/esp/Personal/personas/cbreto/files/teaching/… The beta in my case is not equal to 1, but the presentation covers the basic GARCH(1,1), while I am working with GJR-GARCH(1,1). $\endgroup$
    – Masher
    Dec 28, 2015 at 14:37
  • $\begingroup$ Ha! Notice that the presentation says $\alpha=0$ and $\beta=1$. On that case volatility is constant. That should be straightforward to see from the last equality. But let me know if you have any issues. $\endgroup$
    – phdstudent
    Jan 18, 2016 at 11:48
  • 1
    $\begingroup$ The presentation you link makes some inaccurate statements. For example the common mistake that the condition $\alpha+\beta=1$ implies non-stationarity, something that Nelson showed is wrong since 1990 (the correct is that $\alpha+\beta<1$ implies cov stationarity, nec and suff, cov stationarity tighter than stationarity, correct nec and suff condition for stationarity $E[\ln(\alpha u_t^2+\beta)]<0$). $\endgroup$
    – Kiwiakos
    Mar 13, 2016 at 0:49

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

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