MCMC Output for Bayesian Source Apportionment Model

Full MCMC output from a dependent Bayesian Dirichlet Process model for source apportionment of particle number size distribution. The data accompanies a journal article published in Environmetrics and was generated using the Nimble probabilistic programming language. The output is provided by Oliver Baerenbold of Imperial College London to allow for user reproducibility.

Use Cases

• Reproducing the analysis from the Environmetrics article based on the full model output
• Conducting sensitivity analysis on the Bayesian model based on the provided MCMC chains
• Developing new diagnostic or visualization methods for MCMC output based on the provided samples
• Teaching advanced Bayesian computation using a real-world environmental science example based on the described model

Strengths

• Provides full, not summary, MCMC output, enabling detailed reproducibility checks
• Accompanies a peer-reviewed journal article in a recognized special issue on Environmental Data Science
• Model was implemented using the Nimble probabilistic programming language, a standard tool in the field

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

Oliver Baerenbold, Imperial College London

Collection Method

Generated by running a Bayesian model using the Nimble probabilistic programming language.