[R-SIG-Finance] Help! NAs and errors in ugarchfit ...

[alexios ghalanos]

Looking at the log-likelihood the solver did not find a set of feasible 
starting points (and the default ones used by the model did not work).
Try:
1. Some different starting values using the setstart<- method on the spec.
2. A different solver (you have "solnp","nlminb", 10 subsolvers with 
"nloptr", "gosolnp"). Each solver has its own tuning parameters. Try to 
adjust them to suit your problem.
3. A more parsimonious/simple model first.
4. Check your data for cleanliness (NAs, lost of consecutive zeros etc).

In future, as mentioned multiple time on this forum, do have the 
courtesy of signing your email with your real name.

Regards,
Alexios


On 29/04/2012 02:46, Luna wrote:
> Hi all,
>
> Could you please help me?
>
> I am fitting the GJRGARCH model to 60000 data points of 15min bar
> log-return data... and I got the following error message... with lots of NA
> results...
>
> What shall I do?
>
> Thanks a lot!
>
>
>> spec = ugarchspec(variance.model = list(model = "gjrGARCH"),
> distribution.model = "sged")
>> fit = ugarchfit(data = dLogRets, spec = spec)
>>
>> fit
>
> *---------------------------------*
> *          GARCH Model Fit        *
> *---------------------------------*
>
> Conditional Variance Dynamics
> -----------------------------------
> GARCH Model : gjrGARCH(1,1)
> Mean Model : ARFIMA(1,0,1)
> Distribution : sged
>
> Optimal Parameters
> ------------------------------------
>          Estimate  Std. Error  t value Pr(>|t|)
> mu     -0.000012          NA       NA       NA
> ar1     0.038942          NA       NA       NA
> ma1     0.038334          NA       NA       NA
> omega   0.000000          NA       NA       NA
> alpha1  0.050000          NA       NA       NA
> beta1   0.900000          NA       NA       NA
> gamma1  0.050000          NA       NA       NA
> skew    1.000000          NA       NA       NA
> shape   2.000000          NA       NA       NA
>
> Robust Standard Errors:
>          Estimate  Std. Error  t value Pr(>|t|)
> mu     -0.000012          NA       NA       NA
> ar1     0.038942          NA       NA       NA
> ma1     0.038334          NA       NA       NA
> omega   0.000000          NA       NA       NA
> alpha1  0.050000          NA       NA       NA
> beta1   0.900000          NA       NA       NA
> gamma1  0.050000          NA       NA       NA
> skew    1.000000          NA       NA       NA
> shape   2.000000          NA       NA       NA
>
>   failed to invert hessian
> LogLikelihood : -1.1
>
> Information Criteria
> ------------------------------------
>
> Akaike       0.00037884
> Bayes        0.00187841
> Shibata      0.00037879
> Hannan-Quinn 0.00084718
>
> Q-Statistics on Standardized Residuals
> ------------------------------------
>        statistic   p-value
> Lag10     26.17 0.0009835
> Lag15     27.71 0.0099253
> Lag20     34.01 0.0125447
>
> H0 : No serial correlation
>
> Q-Statistics on Standardized Squared Residuals
> ------------------------------------
>        statistic p-value
> Lag10     11.53  0.1736
> Lag15     15.75  0.2630
> Lag20     20.97  0.2810
>
> ARCH LM Tests
> ------------------------------------
>               Statistic DoF P-Value
> ARCH Lag[2]      2.860   2  0.2394
> ARCH Lag[5]      6.334   5  0.2751
> ARCH Lag[10]    12.032  10  0.2829
> Error in t.default(grad) : argument is not a matrix
>
> Enter a frame number, or 0 to exit
>
> 1: function (object)
> 2: function (object)
> 3: .nyblomTest(object)
> 4: t(grad)
> 5: t.default(grad)
>
> Selection:
>
> 	[[alternative HTML version deleted]]
>
> _______________________________________________
> R-SIG-Finance at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-finance
> -- Subscriber-posting only. If you want to post, subscribe first.
> -- Also note that this is not the r-help list where general R questions should go.
>