Bayesian Posterior Inference Results for Hospital Transmission Scenarios

A summary of Bayesian posterior inference results from 100 simulation replicates for three bacterial transmission scenarios: hospital-driven, equal, and community-driven. The dataset, created by Sanni Översti and last updated in March 2026, includes metrics on effective sample size, relative error, relative bias, and 95% highest posterior density accuracy. It is a small 5.5 KB Excel file.

Use Cases

• Compare parameter estimation accuracy between hospital-driven, equal, and community-driven transmission scenarios.
• Validate Bayesian inference methods using the reported effective sample size (ESS) and relative error metrics.
• Assess the impact of fixed parameters, like admission and discharge rates, on posterior inference results.

Strengths

• Results are based on 100 simulation replicates per scenario, providing a basis for statistical assessment.
• Includes multiple diagnostic metrics: effective sample size (ESS), relative error, relative bias, and 95% HPD accuracy.
• Explicitly compares three distinct epidemiological scenarios (HDT, ET, CDT).

Limitations

• Row count and specific column names are unknown, limiting suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The 5.5 KB size indicates a very small, likely summary-level dataset with limited scope.

Provenance

Source

figshare, author Sanni Översti

Collection Method

Likely generated from computational simulations of bacterial transmission models.

Freshness

Last updated 2026-03-17 16:41:46; freshness should be verified.