This package offers tools for estimation, forecasting, and simulation of generalized autoregressive score (GAS) models of Creal et al. (2013) and Harvey (2013), also known as dynamic conditional score (DCS) models or score-driven (SD) models.
The key function is gas() which estimates GAS models.
Additional functions include gas_simulate() which simulates GAS models, gas_forecast() which forecasts GAS models, gas_filter() which obtains filtered time-varying parameters of GAS models, and gas_bootstrap() which bootstraps coefficients of GAS models.
The list of supported distributions can be obtained by distr().
The functions working with distributions are distr_density() which computes the density, distr_mean() which computes the mean, distr_var() which computes the variance, distr_score() which computes the score, distr_fisher() which computes the Fisher information, and distr_random() which generates random observations.
The included datasets are bookshop_orders which contains times of antiquarian bookshop orders, ice_hockey_championships which contains the results of the Ice Hockey World Championships, and toilet_paper_sales which contains daily sales of toilet paper.
Maintainer: Vladimír Holý vladimir.holy@vse.cz (ORCID)
Creal, D., Koopman, S. J., and Lucas, A. (2013). Generalized Autoregressive Score Models with Applications. Journal of Applied Econometrics, 28(5), 777–795. tools:::Rd_expr_doi("10.1002/jae.1279").
Harvey, A. C. (2013). Dynamic Models for Volatility and Heavy Tails: With Applications to Financial and Economic Time Series. Cambridge University Press. tools:::Rd_expr_doi("10.1017/cbo9781139540933").
Useful links: