Generalized Autoregressive Score Models in R: The GAS Package

Ardia, David; Boudt, Kris; Catania, Leopoldo

doi:10.2139/ssrn.2825380

Cited by 15 publications

(37 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In Table 3, we present the maximum likelihood estimates of the GAS (1,1) coefficients, together with the standard error and the t value of the estimates as well as their p ‐values. The R package is used for the estimation under the GAS framework (Ardia, Boudt, & Catania, 2016). The ω have a high p ‐value for all assets, which is common for financial data.…”

Section: Resultsmentioning

confidence: 99%

A value‐at‐risk computation based on heavy‐tailed distribution for dynamic conditional score models

2020

View full text Add to dashboard Cite

The purpose of this study is to evaluate the estimating ability of GAS models in the computation of the value‐at‐risk by applying the extreme‐value theory. Our approach is the limiting result of an infinity shift of location. In this work, we use the generalized pareto distribution since it plays a central role in modelling heavy tail phenomena in many applications. A simulation study is performed to assess the estimated value‐at‐risk. Moreover, we examine the performance of the proposed method with daily returns of three stock market indices. The results prove that the presented approach gives good predictions for all indices.

show abstract

Section: Resultsmentioning

confidence: 99%

A value‐at‐risk computation based on heavy‐tailed distribution for dynamic conditional score models

2020

View full text Add to dashboard Cite

show abstract

“…The optimal number of clusters has been decided according to the fuzzy silhouette criterion whose results are showed in the Tab. 4 Moreover, in the Tab. 5 we reported the uncertainty about clustering assignment in such scenario.…”

Section: Fuzzy Clustering Under T-student Densitymentioning

confidence: 99%

Model-based fuzzy time series clustering of conditional higher moments

Cerqueti¹,

Giacalone²,

Mattera³

2021

Preprint

View full text Add to dashboard Cite

This paper develops a new time series clustering procedure allowing for heteroskedasticity, non-normality and model's non-linearity. At this aim, we follow a fuzzy approach. Specifically, considering a Dynamic Conditional Score (DCS) model, we propose to cluster time series according to their estimated conditional moments via the Autocorrelation-based fuzzy C-means (A-FCM) algorithm. The DCS parametric modelling is appealing because of its generality and computational feasibility. The usefulness of the proposed procedure is illustrated using an experiment with simulated data and several empirical applications with financial time series assuming both linear and nonlinear models' specification and under several assumptions about time series density function.

show abstract

“…It is used to represent all forms of time-series data, which can be either real-valued, integervalued or bounded. The values should ensure conditional density when the score function is well defined [14]. The main challenge of using the GAS model on non-linear data is to evaluate the score and the maximum likelihood estimation.…”

Section: Introductionmentioning

confidence: 99%

Performance monitoring of wind turbines using advanced statistical methods

Kushwah

Wadhvani

2019

Sādhanā

View full text Add to dashboard Cite

Estimation of wind power generation for grid interface helps in calculation of the annual energy production, which maintains the balance between electricity production and its consumption. For this purpose, accurate wind speed forecasting plays an important role. In this paper, linear statistical predictive models such as autoregressive integrated moving average (ARIMA), generalized autoregressive score (GAS) model and a GAS model with exogenous variable x (GASX) have been applied for accurate wind speed forecasting. Along with this, a non-linear statistical predictive modelling technique called non-linear GASX (NLGASX) has been proposed and applied to model non-linear time-series data. Furthermore, the proposed NLGASX model is optimized using modelling techniques based on neural networks, namely Sigmoid, TANH, Softmax and RELU. The proposed optimized NLGASX model performs far better as compared with other models. Wind speed is also used as an input to wind power curve model for predicting the wind power. According to the predicted wind power the annual energy has been calculated.

show abstract

Generalized Autoregressive Score Models in R: The GAS Package

Cited by 15 publications

References 39 publications

A value‐at‐risk computation based on heavy‐tailed distribution for dynamic conditional score models

A value‐at‐risk computation based on heavy‐tailed distribution for dynamic conditional score models

Model-based fuzzy time series clustering of conditional higher moments

Performance monitoring of wind turbines using advanced statistical methods

Contact Info

Product

Resources

About