Input validation: Added comprehensive validation
for rwa() parameters including conf_level,
n_bootstrap, non-numeric variables, zero-variance
variables, and singular correlation matrices with informative error
messages
Code refactoring: Consolidated duplicate RWA
calculation code in bootstrap functions into a single internal
helper
Documentation: Added links to pkgdown site in
README; fixed internal function documentation
Bug Fixes
Fixed flaky bootstrap test by using a fixed random seed for
reproducibility (#20)
Tests
Added extensive tests for input validation and edge cases
(collinearity, small samples, invalid parameters)
rwa 0.1.0
New Features
Bootstrap confidence intervals: Added
bootstrap = TRUE parameter to rwa() for
statistical significance testing of relative weights
Result sorting: Added sort = TRUE
parameter to automatically sort results by importance (descending
order). Set sort = FALSE to preserve original predictor
order
Comprehensive vignette: New detailed documentation
covering methodology, examples, and best practices
Enhanced documentation: Updated README and function
documentation
Technical Improvements
Package compliance: Updated DESCRIPTION with proper
Authors@R field for CRAN submission
CI/CD: Enhanced GitHub Actions workflow with
vignette building support
Dependencies: Added boot,
purrr, and utils packages for bootstrap
functionality
Code quality improvements: Fixed long lines in R
code to meet CRAN standards
Documentation cleanup: Improved code formatting and
removed unused variables
Enhanced vignette formatting: Cleaned up formatting
in comprehensive vignette documentation
Bug Fixes
Fixed vignette compilation issues
Resolved R CMD check warnings and notes
Removed unused variables to eliminate R CMD check notes