Package: GAS 0.3.4.1

Leopoldo Catania

GAS: Generalized Autoregressive Score Models

Simulate, estimate and forecast using univariate and multivariate GAS models as described in Ardia et al. (2019) <doi:10.18637/jss.v088.i06>.

Authors:Leopoldo Catania [aut, cre], David Ardia [ctb], Kris Boudt [ctb]

GAS_0.3.4.1.tar.gz
GAS_0.3.4.1.tar.gz(r-4.5-noble)GAS_0.3.4.1.tar.gz(r-4.4-noble)
GAS_0.3.4.1.tgz(r-4.4-emscripten)GAS_0.3.4.1.tgz(r-4.3-emscripten)
GAS.pdf |GAS.html✨
GAS/json (API)

# Install 'GAS' in R:
install.packages('GAS', repos = 'https://cloud.r-project.org')

Bug tracker:https://github.com/leopoldocatania/gas/issues6 issues

Uses libs:
  • openblas– Optimized BLAS
  • c++– GNU Standard C++ Library v3
Datasets:
  • Goals - Data: Goals scored by England against Scotland in international football matches.
  • StockIndices - Data: Daily logarithmic returns in percentage points of the DAX, FTSEMIB and CAC40 from 2007-01-03 to 2016-06-24
  • cpichg - Data: Quarterly logarithmic change in percentage points of the Consumer Price Index for All Urban Consumers: All Items (CPIAUCSL) from 1947-04-01 to 2016-05-01
  • dji30ret - Data: Dow Jones 30 Constituents Closing Value Log Return in percentage points
  • sp500ret - Data: Daily logarithmic returns in percentage points of the S&P500 index from 1950-01-04 to 2016-06-24
  • sp500rv - Data: SP500 Daily 5 minutes Realized Volatility from 2000-01-03 to 2000-01-10
  • tqdata - Data from Bien et al (2011).
  • usunp - US Monthly Civilian Unemployment Rate (UNRATE) from 1948-01-01 to 2016-05-01

On CRAN:

Conda:

openblascpp

3.20 score 1 packages 1.1k downloads 165 mentions 63 exports 10 dependencies

Last updated 7 months agofrom:5b6062863b. Checks:2 OK, 1 NOTE. Indexed: no.

TargetResultLatest binary
Doc / VignettesOKMar 04 2025
R-4.5-linux-x86_64NOTEMar 04 2025
R-4.4-linux-x86_64OKMar 04 2025

Exports:BacktestDensityBacktestVaRbuild_vRcoefConfidenceBandsconvergenceddist_Multiddist_UniDistInfoDistLabelsDistNameDistParametersDistScalingTypeDistTypeESfn.optimfn.solnpFZLossgetFilteredParametersgetForecastgetMomentsgetObsIM_UniLogScoreLowerALowerBLowerNuMapR_Cmdist_UnimGASMultiForcastMultiGASFitMultiGASForMultiGASRollMultiGASSimMultiGASSpecMultiMapParametersMultiUnmapParametersNumberParameterspdist_UnipitPIT_testplotqdist_UniquantileQuantilesrdist_Multirdist_UniresidualsScore_MultiScore_UnishowuGASMultiForcastUniGASFitUniGASForUniGASRollUniGASSimUniGASSpecUniMapParametersUniUnmapParametersUnMapR_CUpperAUpperBUpperNu

Dependencies:cubaturelatticeMASSnumDerivRcppRcppArmadilloRsolnptruncnormxtszoo

Citation

To cite GAS in publications use:

Ardia D, Boudt K, Catania L (2019). “Generalized Autoregressive Score Models in R: The GAS Package.” Journal of Statistical Software, 88(6), 1–28. doi:10.18637/jss.v088.i06.

Corresponding BibTeX entry: 

  @Article{,
    title = {Generalized Autoregressive Score Models in {R}: The {GAS}
      Package},
    author = {David Ardia and Kris Boudt and Leopoldo Catania},
    journal = {Journal of Statistical Software},
    year = {2019},
    volume = {88},
    number = {6},
    pages = {1--28},
    doi = {10.18637/jss.v088.i06},
  }

Readme and manuals

GAS

GAS implements the Generalized Autoregressive Score (GAS) framework in R. The GAS package provides functions to simulate univariate and multivariate GAS processes, estimate the GAS parameters and to make time series forecasts. Full description of the algorithm and numerous applications are available in Ardia et al. (2018) and Ardia et al. (2019).

Please cite the package in publications!

By using GAS you agree to the following rules:

  1. You must cite Ardia et al. (2019) in working papers and published papers that use GAS.
  2. You must place the following URL in a footnote to help others find GAS: https://CRAN.R-project.org/package=GAS.
  3. You assume all risk for the use of GAS.

Ardia, D., Boudt, K., Catania, L. (2018).
Downside Risk Evaluation with the R Package GAS.
R Journal, 10(2), 410-421.
https://doi.org/10.32614/RJ-2018-064

Ardia, D., Boudt, K., Catania, L. (2019).
Generalized autoregressive score models in R: The GAS package.
Journal of Statistical Software, 88(6), 1-28.
https://doi.org/10.18637/jss.v088.i06

Help Manual

Help pageTopics
Generalized Autoregressive Score models in RGAS-package GAS
Backtest a series of one-step ahead density predictions.BacktestDensity
Backtest Value at Risk (VaR)BacktestVaR
Build confidence bands for the filtered parametersConfidenceBands
Data: Quarterly logarithmic change in percentage points of the Consumer Price Index for All Urban Consumers: All Items (CPIAUCSL) from 1947-04-01 to 2016-05-01cpichg
Information for the supported distributionsDistInfo DistLabels DistName DistParameters DistScalingType DistType NumberParameters
Distributions of the GAS packageddist_Multi ddist_Uni distributions IM_Uni mdist_Uni pdist_Uni qdist_Uni Quantiles rdist_Multi rdist_Uni rmvt_mat Score_Multi Score_Uni
data: Dow Jones 30 Constituents Closing Value Log Return in percentage pointsdji30ret
A wrapper to the optim function.fn.optim
A wrapper to the solnp function of the 'Rsolnp' package of Ghalanos and Theussl (2016).fn.solnp
Fissler and Ziegel (2016) (FZ) joint loss function for Value at Risk and Expected Shortfall.FZLoss
data: Goals scored by England against Scotland in international football matches.Goals
Class for the Multivariate GAS fitted objectcoef,mGASFit-method convergence convergence,mGASFit-method getFilteredParameters,mGASFit-method getMoments,mGASFit-method getObs,mGASFit-method mGASFit mGASFit-class plot,mGASFit,missing-method residuals,mGASFit-method show,mGASFit-method summary,mGASFit-method
Class for the Multivariate GAS Forecast objectgetForecast,mGASFor-method getMoments,mGASFor-method LogScore,mGASFor-method mGASFor mGASFor-class plot,mGASFor,missing-method show,mGASFor-method
Class for the Multivariate GAS Rolling objectcoef,mGASRoll-method getForecast,mGASRoll-method getMoments,mGASRoll-method LogScore,mGASRoll-method mGASRoll mGASRoll-class plot,mGASRoll,missing-method residuals,mGASRoll-method show,mGASRoll-method
Class for Multivariate GAS Simulationcoef,mGASSim-method getFilteredParameters,mGASSim-method getMoments,mGASSim-method getObs,mGASSim-method mGASSim mGASSim-class plot,mGASSim,missing-method show,mGASSim-method
Class for the Multivariate GAS model specificationmGASSpec mGASSpec-class show,mGASSpec-method
Estimate multivariate GAS modelsMultiGASFit
Forecast with multivariate GAS modelsmGASMultiForcast MultiGASFor
Rolling forecast with multivariate GAS modelsMultiGASRoll
Simulate multivariate GAS processesMultiGASSim
Multivariate GAS specificationMultiGASSpec
Mapping function for univariate distributionsbuild_mR build_vR MapR_C MultiMapParameters
Inverse of MultiMapParametersMultiUnmapParameters UnMapR_C
Numerical bounds imposed in parameters transformation.LowerA LowerB LowerNu NumericalBounds UpperA UpperB UpperNu
Goodness of fit for conditional densitiesPIT_test
Plot output from an object of the from the GAS package.plot PlotMenu
Data: Daily logarithmic returns in percentage points of the S&P500 index from 1950-01-04 to 2016-06-24sp500ret
Data: SP500 Daily 5 minutes Realized Volatility from 2000-01-03 to 2000-01-10sp500rv
Data: Daily logarithmic returns in percentage points of the DAX, FTSEMIB and CAC40 from 2007-01-03 to 2016-06-24StockIndices
Data from Bien et al (2011).tqdata
Class for the univariate GAS fitted objectcoef,uGASFit-method convergence,uGASFit-method ES ES,uGASFit-method getFilteredParameters getFilteredParameters,uGASFit-method getMoments getMoments,uGASFit-method getObs getObs,uGASFit-method pit pit,uGASFit-method plot,uGASFit,missing-method quantile,uGASFit-method residuals residuals,uGASFit-method show,uGASFit-method summary,uGASFit-method uGASFit uGASFit-class
Class for the univariate GAS forecast objectES,uGASFor-method getForecast,uGASFor-method getMoments,uGASFor-method getObs,uGASFor-method LogScore,uGASFor-method pit,uGASFor-method plot,uGASFor,missing-method quantile,uGASFor-method show,uGASFor-method uGASFor uGASFor-class
Class for the univariate GAS rolling objectcoef,uGASRoll-method ES,uGASRoll-method getForecast getForecast,uGASRoll-method getMoments,uGASRoll-method getObs,uGASRoll-method LogScore LogScore,uGASRoll-method pit,uGASRoll-method plot,uGASRoll,missing-method quantile,uGASRoll-method residuals,uGASRoll-method show,uGASRoll-method uGASRoll uGASRoll-class
Class for Univariate GAS Simulationcoef,uGASSim-method ES,uGASSim-method getFilteredParameters,uGASSim-method getMoments,uGASSim-method getObs,uGASSim-method plot,uGASSim,missing-method quantile,uGASSim-method show,uGASSim-method uGASSim uGASSim-class
Class for the univariate GAS model specificationshow,uGASSpec-method uGASSpec uGASSpec-class
Estimate univariate GAS modelsUniGASFit
Forecast with univariate GAS modelsuGASMultiForcast UniGASFor
Rolling forecast with univariate GAS modelsUniGASRoll
Simulate Univariate GAS processesUniGASSim
Univariate GAS specificationUniGASSpec
Mapping function for univariate distributionsUniMapParameters
Unmapping function for univariate distributions, i.e. inverse of UniMapParametersUniUnmapParameters
US Monthly Civilian Unemployment Rate (UNRATE) from 1948-01-01 to 2016-05-01usunp