A methodological article by David J. Nott connecting Bayes' linear analysis and regression-adjustment approximate Bayesian computation (ABC) techniques. The work proposes a new method for combining high-dimensional, regression-adjustment ABC with lower-dimensional approaches to improve joint posterior estimation. Supplementary materials for the article are available online.
Use Cases
- Exploratory analysis of high-dimensional Bayesian models based on regression-adjustment ABC methods.
- Improving joint posterior estimates by combining high-dimensional ABC with lower-dimensional marginal analyses.
- Comparing moment summaries from regression-adjustment ABC to adjusted expectation and variance from Bayes' linear analysis.
Strengths
- Article is Open Access (green), indicating free availability.
- Method is illustrated with several examples, suggesting practical application.
Limitations
- Row count and dataset size are unknown, which may limit suitability assessment.
- Column-level documentation is absent; field semantics must be inferred after download.
- Last update date is unknown; freshness unverified.
Provenance
- Source
- David J. Nott
- Collection Method
- Methodological research article.