WAIC Values for Spatiotemporal Models of Respiratory Deaths in California

California monthly time series of respiratory-related deaths are modeled using a novel spatiotemporal procedure. The dataset contains WAIC (Watanabe-Akaike Information Criterion) values for the proposed model and alternative reference models. The data and code were authored by Jeffrey Wu and published on figshare in 2026.

Use Cases

• Comparing model fit for spatiotemporal models based on WAIC values.
• Evaluating the performance of a novel multi-step modeling procedure against reference models.
• Assessing model coverage properties for forecasting respiratory mortality.
• Validating spatiotemporal models that incorporate social deprivation and air quality variables.

Strengths

• Data is associated with a published methodological paper describing a novel modeling procedure.
• Includes WAIC values for multiple models, enabling direct statistical comparison.
• Released under a permissive CC-BY-4.0 license.

Limitations

• Dataset is very small at 5.5 KB, containing only summary model comparison metrics.
• Row count and column-level documentation are unknown; data structure must be inspected after download.
• The underlying raw data for the time series is stored in a separate repository.

Provenance

Source

figshare, authored by Jeffrey Wu.

Collection Method

Likely generated as part of a statistical modeling study comparing spatiotemporal models.

Freshness

Last updated 2026-05-21 07:31:26; freshness should be verified.

Geography

California, USA.