Estimates cumulative distribution functions and quantiles under
local differential privacy. Provides isotonic and divide-and-conquer
distribution estimators, aggregation across independent surveys, online
inference for single and multiple quantiles, and asymptotic quantile
confidence sequences. Also estimates category-specific subdistribution
functions under asymmetric local privacy. Binary and categorical
randomization mechanisms support these procedures. Distribution
estimators operate on privatized reports; quantile interfaces simulate
sequential local randomization internally. Published methodological
sources include Liu et al. (2023)
< https://proceedings.mlr.press/v202/liu23q.html>, Liu, Hu and Kong (2024)
< https://proceedings.mlr.press/v235/liu24z.html>, Cai et al. (2025)