cvequality: R Package for Testing Equality of Coefficients of Variation

Ben Marwick's R package provides statistical tests for comparing coefficients of variation across multiple groups. It implements Feltz and Miller's (1996) asymptotic test and Krishnamoorthy and Lee's (2014) modified signed-likelihood ratio test. The package is sourced from the paperswithcode platform, which aggregates resources for AI/ML practitioners.

Use Cases

• Compare relative variability in astronomical measurements across different observation groups.
• Test for significant differences in experimental precision between multiple laboratory conditions.
• Validate the homogeneity of variance assumptions in statistical models using the coefficient of variation.
• Apply the modified signed-likelihood ratio test for robust hypothesis testing on grouped data.

Strengths

• Implements two established statistical methods from peer-reviewed publications (1996, 2014).
• Includes a vignette for detailed documentation and full citation details.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Last update date is unknown; freshness unverified.

Provenance

Source

paperswithcode

Collection Method

Software package aggregation for AI/ML resources.