Changes in version 3.1.0 (2026-03-19) Changed o *Breaking*: robScale uses the bias-corrections factors by default. Testing shows that the improvement is measurable and significant. o *Breaking*: robLoc and robScale refactored to move lesser-used options into an opts list and have a consistent parameter order across the package. o Function examples now better demonstrate their usefulness. o Refactored and updated unit tests. Fixed o Corrected and updated documentation. Removed o Removed unused, unexposed functions medianR and madf carried over from older development. Changes in version 3.0.0 (2026-03-18) Added o New exported functions madn and admn providing high-precision small-sample bias-corrected versions of the MAD and ADM. o New optional constants for bias reduction in robScale (via usefctrs and madfctrs). Changed o *Major rewrite*: Complete port of the computational core to modern Fortran 90, including a new optimized quicksort-based median algorithm for small n. This gives substantially better performance, cleaner code, and improved NA handling in line with base R. o *Breaking*: All small-sample (n <= 9) and asymptotic bias-correction factors for madn, admn, and robScale (both known and unknown location cases) were recomputed using 200 million Monte Carlo simulations (small n) and 16.5 million simulations per sample size (asymptotic: 10 <= n <= 100). The new 4-decimal “AA” constants have Monte Carlo standard errors between 2e-5 and 9.1e-5. The original Croux & Rousseeuw (“CR”) factors remain available as an option in madn and robScale (Issue #1; thank you @filiporn). o *Breaking*: robLoc and robScale now use the new madn/admn internally with improved very-small-sample logic. The new “AA” factors are now the default. o Unit tests expanded and modernized. o Documentation, GitHub workflows, and package metadata updated. Fixed o Various spelling, punctuation, and metadata issues. o Corrected package metadata unit test. Changes in version 2.0.0 (2024-06-20) Changed o *Breaking:* In robScale, the constant representing the denominator for x (see equation 26)-which allows for beta = integral of rho(u) d Phi(u) = 0.5-was calculated to greater precision than the four digits shown in the paper. This changes results slightly, which is why the major version has been incremented. o Updated documentation. o Updated unit tests. o Expanded package metadata tests. o Use native CRAN DOI. Added o Added rhub checking. Changes in version 1.0.6 (2024-02-01) Changed o Add SPDX codes to source files. o Update README, GitHub actions, and unit tests. Changes in version 1.0.5 (2023-02-01) Added o Explicitly mention use case for package to be 3-8 samples. o Note that asymptotic constant for adm may not apply with few samples. Changed o Update README. o Update GitHub actions. o Make code more compliant with style guide. o CITATION updated to use bibentry per CRAN request. Changes in version 1.0.4 (2022-04-04) Changed o Explicitly use integers in count and lengths. o Use singleton logical comparisons for short-circuit. o Update README for Best Practice. Added o Added Best Practice badge to README. Changes in version 1.0.3 (2022-01-19) Changed o Converted test suite to tinytest to reduce dependencies. o Augmented citation with DOI. Changes in version 1.0.2 (2021-12-14) Fixed o Corrected adm documentation. Changed o Cleaned up help files and README. o Cleaned up source code and added SPDX identifiers. o Moved continuous integration to GitHub Actions. Changes in version 1.0.1 (2020-11-10) Fixed o Corrected CRAN requests. Changes in version 1.0.0 Changed o Considered mature enough for official release. o Changed tests to be testthat 3rd edition compliant. o Changed default maxit to 80. Added o Added AppVeyor. o Added more tests. Fixed o Updated README. Changes in version 0.0.2 (2020-06-03) Fixed o Minor corrections in DESCRIPTION for CRAN. Changes in version 0.0.1 Added o Initial version.