The BMA package provides tools for Bayesian model averaging and variable selection. It was authored by Adrian Raftery and is hosted on the paperswithcode platform. The package supports linear models, generalized linear models, and survival models like Cox regression.
Use Cases
- Perform variable selection for linear regression based on Bayesian model averaging.
- Average predictions from multiple generalized linear models using Bayesian methods.
- Apply Bayesian model averaging to survival analysis via Cox regression.
Strengths
- Package authored by a recognized statistician, Adrian Raftery.
- Supports multiple model families: linear, generalized linear, and survival models.
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.
Provenance
- Source
- paperswithcode
- Collection Method
- Software package for statistical analysis.
- Time Range
- null
- Freshness
- Last update date is unknown; freshness unverified.
- Geography
- null