Andrey Akinshin
aakinshin.net · Personal blog · on HN since 2016
Andrey Akinshin writes about statistics, performance benchmarking, and .NET internals, including quantile estimation algorithms.
What HN saysHN links it for quantile and median estimation, such as the P² algorithm, in threads about approximating medians without storing all values.
19HN people shared it
2linked it in comments
25stories submitted
305story points
11 months agolast shared
2016people per year2026
Most-shared posts
- 1Normality Is a Myth4 people · 5 points · first shared 2019 · discussion on HN
- 2P² quantile estimator – estimating the median without storing values2 people · 136 points · first shared 2020 · 48 comments on HN
- 3Statistical Approaches for Performance Analysis2 people · 6 points · first shared 2020 · discussion on HN
- 4Reflecting on performance testing2 people · 3 points · first shared 2017 · discussion on HN
- 5DateTime under the hood2 people · 2 points · first shared 2016 · discussion on HN
- 665535 interfaces ought to be enough for anybody1 people · 131 points · first shared 2017 · 79 comments on HN
- 7Why is NuGet search in Rider so fast?1 people · 4 points · first shared 2017 · discussion on HN
- 8Fast moving median and quantile estimator1 people · 3 points · first shared 2020 · discussion on HN
- 9Stopwatch Under the Hood (2016)1 people · 2 points · first shared 2025 · discussion on HN
- 10Misleading standard deviation1 people · 2 points · first shared 2021 · 1 comments on HN
- 11Stopwatch under the hood1 people · 2 points · first shared 2016 · discussion on HN
- 12Analyzing distribution of Mono GC collections1 people · 2 points · first shared 2018 · discussion on HN
- 13Lowland Multimodality Detection1 people · 1 points · first shared 2020 · discussion on HN
- 14Plain-text summary notation for multimodal distributions1 people · 1 points · first shared 2020 · discussion on HN
- 15NuGet2 and a DirectorySeparatorChar bug1 people · 1 points · first shared 2017 · discussion on HN
What HN people wrote when they linked it
throwaway_2494 · 2024-07-25
See also the Greenwald Khanna quantile estimator, an online algorithm which can compute any quantile within a given ϵ.
https://aakinshin.net/posts/greenwald-khanna-quantile-estimator/
menaerus · 2024-01-05
It certainly is possible to approximate the median: https://aakinshin.net/posts/p2-quantile-estimator/
A quick search shows that Boost.Accumulators have several median estimation implementations available to choose from: https://www.boost.org/doc/libs/1_84_0/doc/html/accumulators/user_s_gui…
> Median estimation based on the P^2 quantile estimator, the density estimator, or the P^2 cumulative distribution estimator.