On The Accuracy of GARCH Estimation in R Packages

Chelsey Hill; B. D. McCullough

Chelsey Hill Department of Decision Sciences & MIS, Drexel University, United States
B. D. McCullough Department of Decision Sciences & MIS, Drexel University, United States

Keywords: Algorithms, Benchmark, Software Accuracy, GARCH

Abstract

The R software is commonly used in applied finance and generalized autoregressive conditionally heteroskedastic (GARCH) estimation is a staple of applied finance; many papers use R to compute GARCH estimates. While R offers three different packages that compute GARCH estimates, they are not equally accurate. We apply the FCP GARCH benchmark (Fiorentini, Calzolari and Panattoni, 1996), proposed by McCullough and Renfro (1999), which uses the Bollerslev and Ghysels (1996) daily returns data, on three R packages: fGarch, rugarch, and tseries.

References

Bollerslev, T. (1986). Generalized Autoregressive Conditional Heteroscedasticity. Journal of Econometrics, 31:307–327.

Bollerslev, T. and Ghysels, E. (1996). Periodic Autoregressive Conditional Heteroscedasticity. Journal of Business and Economic Statistics, 14:139–151.

Brooks, C. (1997). GARCH Modelling in Finance: A Review of the Software Options. Economic Journal, 107(443):1271–1276.

Engle, R. (1982). Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation. Econometrica, 50(4):987–1008.

Engle, R. (2001). GARCH 101: The Use of ARCH/GARCH Models in Applied Econometrics. Journal of Economic Perspectives, 15(4):157–168.

Engle, R. and Bollerslev, T. (1986). Modelling the Persistence of Conditional Variances. Econometric Reviews, 5(1):1–50.

Fiorentini, G., Calzolari, G., and Panattoni, L. (1996). Analytic Derivatives and the Computation of GARCH Estimates. Journal of Applied Econometrics, 11:399–417.

Ghalanos, A. (2017). Introduction to the rugarch package. (Version 1.3-8). https://cran.r-project.org/web/packages/rugarch/.

Glosten, L. R., Jagannathan, R., and Runkle, D. E. (1993). On the Relation between the Expected Value and the Volatility of the Nominal Excess Return on Stocks. Journal of Finance, 48(5):1779–1801.

McCullough, B. D. (2004). Some Details of Nonlinear Estimation. In Altman, M., Gill, J., and McDonald, M. P., editors, Numerical Issues in Statistical Computing for the Social Sciences, pages 199–218. John Wiley & Sons, New York.

McCullough, B. D. and Renfro, C. G. (1999). Benchmarks and Software Standards: A Case Study of GARCH Procedures. Journal of Economic and Social Measurement, 25(2):59–71.

McCullough, B. D. and Renfro, C. G. (2000). Some Numerical Aspects of Nonlinear Estimation. Journal of Economic and Social Measurement, 26(1):63–77.

McCullough, B. D. and Vinod, H. D. (2003a). Comment: Econometrics and Software. Journal of Economic Perspectives, 17(1):223–224.

McCullough, B. D. and Vinod, H. D. (2003b). Verifying the Solution from a Nonlinear Solver: A Case Study. American Economic Review, 93(3):873–892.

McCullough, B. D. and Vinod, H. D. (2004). Verifying the Solution from a Nonlinear Solver: A Case Study: Reply. American Economic Review, 94(1):400–403.

Nash, J. C. (2014). On Best Practice Optimization Methods in R. Journal of Statistical Software, 60(2):1–14.

Nelson, D. B. (1991). Conditional Heteroskedasticity in Asset Returns: A New Approach. Econometrica, 59(2):347–370.

Soito, L. and Hwang, L. J. (2016). Citations for Software: Providing Identification, Access and Recognition for Research Software. International Journal of Digital Curation, 11(2):48–63.

Trapletti, A. and Hornik, K. (2018). tseries: Time Series Analysis and Computational Finance. R package version 0.10-42. https://cran.r-project.org/package=tseries.

Wuertz, D. and Chalabi, Y. (2016). fGarch: Rmetrics - Autoregressive Conditional Heteroskedastic Modelling. R package version 3010.82.1. https://cran.r-project.org/package=fGarch.