Model Topology Performance Comparison with NLLH, AIC, AICc and BIC Metrics

An overview of performance metrics for different model topologies. The dataset reports NLLH, AIC, AICc, and BIC values, the number of model parameters, and a checkmark indicating if a model reproduces described observations. All values are estimated via maximum likelihood estimation. The dataset was authored by Yuhong Liu and last updated on June 2, 2026.

Use Cases

• Comparing model fit across different topologies based on reported NLLH, AIC, AICc, and BIC values.
• Selecting a model with the optimal trade-off between goodness-of-fit and complexity using the number of parameters and information criteria.
• Validating which model topologies successfully reproduce specific observations as indicated by the checkmark feature.

Strengths

• Provides four standard statistical metrics (NLLH, AIC, AICc, BIC) for model comparison.
• Includes a binary validation indicator (checkmark) for whether models reproduce described observations.
• Released under a permissive CC-BY-4.0 license for reuse.

Limitations

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

Provenance

Source

figshare

Collection Method

Likely compiled from model evaluation results.

Freshness

Last updated 2026-06-02 17:41:41; freshness should be verified.