Welcome to G@RCH for OxMetrics 10

Author and Contributors

Prof. Dr. Sébastien Laurent, the copyright owner of G@RCH, is Professor of Econometrics at Aix-Marseille University.
Sébastien has published more than 50 articles in Journal of Econometrics, Econometric Theory, Journal of Business and Economic Statistics, Journal of Applied Econometrics, Journal of Financial Econometrics, European Economic Review and Journal of Empirical Finance among others and has recently co-edited a handbook on volatility models (Wiley). He is associate editor of Journal of Business and Economic Statistics, International Journal of Forecasting and Journal of Time Series Analysis.

Contributors

Overview

G@RCH 9.0 is a software dedicated to the estimation and the forecasting of univariate and multivariate (G)ARCH models and many of its extensions. It can be used within OxMetrics or via the classic programming way (using OxEdit for instance) for those who have access to the Ox programming language.

The available univariate models are all ARCH-type models. These include ARCH, GARCH, EGARCH, GJR, APARCH, IGARCH, RiskMetrics, FIGARCH, FIEGARCH, FIAPARCH and HYGARCH. They can be estimated by approximate (Quasi-)1.1 G@RCH 3 Maximum Likelihood under one of the four proposed distributions for the errors (Normal, Student-t, GED or skewed-Student). Moreover, ARCH-in-mean models are also available and explanatory variables can enter the conditional mean and/or the conditional variance equations.

G@RCH 9.0 also incorporates multivariate GARCH specifications including the scalar BEKK, diagonal BEKK, full BEKK, RiskMetrics, CCC, DCC, DECO, OGARCH and GOGARCH models.

Finally, h-steps-ahead forecasts of both equations are available as well as many univariate and multivariate miss-specification tests (Nyblom, Sign Bias Tests, Pearson goodness-of-fit, Box-Pierce, Residual-Based Diagnostic for conditional heteroscedasticity, Hosking’s portmanteau test, Li and McLead test, constant correlation test, etc.).

More information is in the G@RCH book.

New in G@RCH 10

• G@RCH 10 is now fully integrated in OxMetrics 10.
• G@RCH 10 includes univariate Multiplicative Error Models (MEM). MEM models are primarily aimed at modeling non-negative time series. The most popular MEM type model is the Autoregressive Conditional Duration (ACD) model of Engle and Russell (1998). G@RCH 9.0 provides no fewer than seven different specifications.
• Mulcom 3.0 is now fully integrated into OxMetrics 10. MulCom is designed for forecasting evaluation. It provides an analysis of whether some among a set of competing models are significantly better than the others, in terms of predictive accuracy. MulCom can also be applied in any setting where one what to compare the means of two or more populations.

  More information is in the MulCom book.

• G@RCH 10 can be used with DataFetch to download data from the internet and then estimate a model on the downloaded data. Several examples are given in Chapter 1 that illustrate how to download data and then estimate a model in the same piece of code.
  1. demo_datafetch_Fred_GARCH.ox downloads daily data of the JPY-USD exchange rate from FRED and then estimates a GARCH(1,1) on the log-returns in %.
  2. demo_datafetch_Quandl_GARCH.ox downloads daily closing prices of AAPL from Quandl and then estimates a GJR(1,1) on the logreturns in %.
  3. demo_datafetch_Quandl_MGARCH.ox downloads daily closing prices of MSFT and GOOGL from Quandl and then estimates a bivariate DCCGARCH(1,1) on the log-returns in %.
  4. demo_datafetch_Quandl_MEM.ox downloads daily volumes of AAPL from Quandl and then estimates an ACD(1,1) on the log of the volume.
  NB. downloading data from Quandl requires an API key. See the Quandl website https://www.quandl.com for more information on how to get an API key. The API key needs to be added to the datafetch/config/create_Quandl_provider.ox file and this file has to be executed before running the above two examples.

More information is in the G@RCH book.

© S Laurent This file last changed .