cdcanthro 0.6.0 (2026-11-16)
- Unrecognized sex codes now produce a warning that reports how many
rows were affected and which values were seen; those rows get NA as
before. Text codes are matched as whole words (m, male, b, boy, f,
female, g, girl, and their plurals, in any case) rather than by first
letter, so a value such as “Masc” is now NA with a warning instead of
being read as male.
- who_z() warns when agedays is negative; those rows get NA as
before.
- cdc_z(): the log form of the z-score used when |L| < 0.01 (CDC
SAS convention) now applies to height only. L for weight is never within
0.19 of zero in the CDC tables, so no weight z-score changes.
- The reference-table lookup in cdc_z() and who_z() is now done by
index rather than a join, which uses less memory on large data. No
computed value changes; the regression and SAS-comparison tests are
unchanged.
- Documentation: the help pages for cdc_z(), who_z() and gradual_z()
have been rewritten with new examples; all_vars outputs, the WHO
adjustment beyond +/-3 SD, and the modified z-scores are now described;
NHanes and who_ref_data document every column; a README was added. The
Hales et al.
(2022) NCHS report on extended BMI metrics is cited alongside Wei et
al.
- The package source is now on GitHub
(https://github.com/CDC-DNPAO/cdcanthro); please report problems at
https://github.com/CDC-DNPAO/cdcanthro/issues.
- The SAS validation fixture was reduced from 100,000 to 10,000
children, cutting the package size from 8.3 MB to 1.2 MB.
cdcanthro 0.5.0 (2026-10-30)
- Zero and negative measurements now become NA rather than producing
Inf or nonsense values.
- Fewer warnings and messages
- Stricter input checks, such as when one column, cdc_z(data, age,
ht), is passed for two measures
- A test suite now exists
cdcanthro 0.4.0 (2026-08-30)
- Add two new functions to the package, who_z and gradual_z.
- who_z calculates z-scores based on the WHO growth standards for
children up to 1826 days (5 years). The CDC recommendation is to use the
WHO charts for children under age 2.0 years, and then to use the CDC
charts for older children. This can result in a discontinuity at age 2.0
years, when the reference standard changes from WHO to CDC.
- gradual_z smooths z-scores between ages 2.0 and 5.0 years using a
weighted average of the WHO and CDC z-scores, reducing the discontinuity
at age 2.0 years. Daymont C, et al. Creation and Evaluation of New
Growth Charts With a Gradual Transition From WHO to CDC Values.
Pediatrics 2025;156(3): e2025070697.
- Modified all functions so that arguments can be quoted or
unquoted
- Added a sex_code argument to cdc_z and who_z that may be useful for
people using 0/1 for coding sex
- Also note that the cdcanthro function will be phased out in the
future, and calling
cdcanthro() now gives a warning. The new name is cdc_z.
cdcanthro 0.3.0
- Added logarithmic form of the z-score calculation when |L| <
0.01, to match the CDC SAS implementation for weight and height. BMI_L
never approaches 0.
- Fixed documentation formatting for DOIs in references.
- If input data has ages outside the reference range [24,240 months),
the function warns about this and gives the N. These rows are kept in
the output.