...one of the most highly
regarded and expertly designed C++ library projects in the
world.
— Herb Sutter and Andrei
Alexandrescu, C++
Coding Standards
boost::accumulators::impl::weighted_tail_quantile_impl — Tail quantile estimation based on order statistics of weighted samples (for both left and right tails)
// In header: <boost/accumulators/statistics/weighted_tail_quantile.hpp> template<typename Sample, typename Weight, typename LeftRight> struct weighted_tail_quantile_impl : public accumulator_base { // types typedef numeric::functional::fdiv< Weight, std::size_t >::result_type float_type; typedef Sample result_type; // public member functions weighted_tail_quantile_impl(dont_care); template<typename Args> result_type result(Args const &) const; };
An estimator of tail quantiles with level
based on order statistics
of weighted samples are given by
(left tail) and
(right tail), where \f[
\lambda = \inf\left\{ l \left| \frac{1}{\bar{w}_n}\sum_{i=1}^{l} w_i \geq \alpha \right. \right\}
\f]
and \f[
\rho = \sup\left\{ r \left| \frac{1}{\bar{w}_n}\sum_{i=r}^{n} w_i \geq (1 - \alpha) \right. \right\},
\f]
being the number of samples and
the sum of all weights.