I want to forecast volatility with GARCH, EGARCH and GJR-GARCH. How do I obtain the RMSE, MAE and MAPE. The problem now is that I am using a mean equation and the values reported in the little table on side are for stock returns. I need the same thing for volatility. Any idea except from calculating them by hand?
I think you have to calculate them yourself. I don't believe there is a canned procedure for this. You can ask in the eviews user forum on the company website.
http://forums.eviews.com/
You would have to Model a GARCH for the same and then obtain an in the sample forecast by using the Forecast Tab .
The command accuracy() under forecast package in R returns a range of forecast accuracy measures including:
- ME: Mean Error
- RMSE: Root Mean Squared Error
- MAE: Mean Absolute Error
- MPE: Mean Percentage Error
- MAPE: Mean Absolute Percentage Error
- MASE: Mean Absolute Scaled Error
- ACF1: Autocorrelation of errors at lag 1.
What I suggest is you may generate the necessary forecasts in EViews and use forecast and actual values to compute the loss measures in R.
accuracy(f, x, test = NULL, d = NULL, D = NULL, ...)
where argument f - forecasts and x - realized values.
MSE: mean square error and MAE: mean absolute error, you can get them by using R-package: rugarch. It is a powerful and easy package for you to fit into the GARCH family and forecast volatility easily. And then you fit the model, the package also helps you to get MSE and MAE, too.
https://cran.r-project.org/web/packages/rugarch/rugarch.pdf
Here is the manual.
For those who are interested in choosing suitable error metrics, such as MAE or MSE, please let me recommend this guide:
Chapter Forecast Evaluation Techniques for I4.0 Systems
And this chapter: Chapter Measuring Forecasting Accuracy: Problems and Recommendations...
EViews Help: Forecast Evaluation
type in google and follow step by step procedure in eviews
- Badges
- Science topic
- Similar topics
- Methodology
- Research Methodology
- Research Papers