Supplementary Data for Bayesian Inference in Nonlinear State Space Models

Alexander Kreuzer from the Technical University of Munich provides R scripts, an R package, and data as supplementary materials for a paper on efficient Gibbs sampling for nonlinear state space models. The data likely contains simulation results and parameters for bivariate dynamic copula and stochastic volatility models. The dataset is associated with an Open Access (green) license.

Use Cases

• Benchmarking new Bayesian sampling algorithms based on the provided simulation study data.
• Estimating parameters for stochastic volatility models with skew Student's t errors using the supplied R package and data.
• Modeling dynamic asymmetric tail dependence in financial time series based on the novel bivariate dynamic mixture copula model.
• Comparing predictive accuracy of state space models against benchmarks like DCC-GARCH or Student's t copula models.

Strengths

• Includes R scripts and a dedicated R package for reproducibility of the proposed methods.
• Data supports a simulation study demonstrating the efficiency of the proposed sampler for bivariate dynamic copula models.
• The associated paper compares the approach to relevant benchmark models with respect to predictive accuracy.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Last update date is unknown; freshness unverified.

Provenance

Source

Alexander Kreuzer, Technical University of Munich

Collection Method

Likely generated for a simulation study and empirical analysis in an academic paper.