Single quantile estimation with the algorithm. More...
#include <statistics_fwd.hpp>
Public Types | |
typedef numeric::functional::fdiv < Sample, std::size_t > ::result_type | float_type |
typedef array< float_type, 5 > | array_type |
typedef float_type | result_type |
typedef mpl::false_ | is_droppable |
Public Member Functions | |
template<typename Args > | |
p_square_quantile_impl (Args const &args) | |
template<typename Args > | |
void | operator() (Args const &args) |
result_type | result (dont_care) const |
detail::void_ | operator() (dont_care) |
detail::void_ | add_ref (dont_care) |
detail::void_ | drop (dont_care) |
detail::void_ | on_drop (dont_care) |
Single quantile estimation with the algorithm.
The algorithm estimates a quantile dynamically without storing samples. Instead of storing the whole sample cumulative distribution, only five points (markers) are stored. The heights of these markers are the minimum and the maximum of the samples and the current estimates of the -, - and -quantiles. Their positions are equal to the number of samples that are smaller or equal to the markers. Each time a new samples is recorded, the positions of the markers are updated and if necessary their heights are adjusted using a piecewise- parabolic formula.
For further details, see
R. Jain and I. Chlamtac, The P^2 algorithm for dynamic calculation of quantiles and histograms without storing observations, Communications of the ACM, Volume 28 (October), Number 10, 1985, p. 1076-1085.
quantile_probability |
typedef array<float_type, 5> boost::accumulators::impl::p_square_quantile_impl< Sample, Impl >::array_type |
typedef numeric::functional::fdiv<Sample, std::size_t>::result_type boost::accumulators::impl::p_square_quantile_impl< Sample, Impl >::float_type |
|
inherited |
typedef float_type boost::accumulators::impl::p_square_quantile_impl< Sample, Impl >::result_type |
|
inline |
References boost::multiprecision::backends::i.
|
inlineinherited |
|
inlineinherited |
|
inlineinherited |
|
inlineinherited |
|
inline |
|
inline |