Spatial Heteroscedasticity Test for Geographically Weighted Regression Models

A test dataset for a proposed residual-based method to detect spatial heteroscedasticity in geographically weighted regression models. The dataset includes simulation results and two real-world examples, authored by Chen jing Chen and shared under a CC-BY-4.0 license on figshare. The method's performance was assessed through simulations, showing high accuracy in detecting complex spatial variance patterns.

Use Cases

• Testing new heteroscedasticity detection methods based on residual trend analysis.
• Benchmarking the performance of spatial statistical tests using the provided simulation results.
• Applying the proposed test to real-world geographical datasets to check for error variance patterns.

Strengths

• The proposed test method is described as having high accuracy and satisfactory power, especially for spatially complicated variance functions.
• Includes simulation comparisons to assess the performance of the proposed statistic.
• Dataset is shared under a permissive CC-BY-4.0 license.

Limitations

• The dataset is very small at 10.3 KB, indicating limited scope.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

figshare

Collection Method

Likely contains simulation data and results from two real-world analyses.

Freshness

Last updated 2026-04-17 11:57:21; freshness should be verified.