Poisson Regression Model Results for France with Rainfall Effect Estimates

Results of Poisson regression models for France, comparing different model setups. Each row represents a specific model configuration, including the Prophet setup and weekly component inclusion. The dataset includes the Akaike Information Criterion (AIC) for model comparison and the estimated percentage change in test numbers associated with 25mm of rainfall. The dataset was authored by Susanna Caruso and last updated on 2026-04-29.

Use Cases

• Compare model performance based on Akaike Information Criterion (AIC) values for different Prophet and weekly component configurations.
• Estimate the impact of rainfall on test numbers based on the reported percentage change with confidence intervals.
• Analyze spatial autocorrelation and area-level random effects from the provided parameter estimates.

Strengths

• Includes a direct model comparison metric via the Akaike Information Criterion (AIC).
• Reports effect sizes for rainfall (25mm) with 95% confidence intervals.
• Provides estimates for spatial autocorrelation and area-level random effect variance.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small at 5.5 KB, indicating limited scope.

Provenance

Source

figshare

Collection Method

Likely contains statistical model outputs from an analysis.

Freshness

Last updated 2026-04-29 17:31:50; freshness should be verified.

Geography

France