[MATH-418] add a storeless version of Percentile

• Type: New Feature
• Status: Closed
• Priority: Major
• Resolution: Fixed
• Affects Version/s: 2.1
• Fix Version/s: 3.4
• Assignee: Unassigned
• Reporter: Luc Maisonobe
• Created: 18/Sep/10 15:51
• Updated: 26/Dec/14 19:50
• Resolved: 21/Jun/14 18:21

Description

The Percentile class can handle only in-memory data.
It would be interesting to use an on-line algorithm to estimate quantiles as a storeless statistic.
An example of such an algorithm is the exponentially weighted stochastic approximation described in a 2000 paper by Fei Chen , Diane Lambert and José C. Pinheiro "Incremental Quantile Estimation for Massive Tracking" which can be retrieved from CiteSeerX at http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.105.1580.

Issue Links

• is duplicated by: MATH-1112 Implementation of Percentile function that does not need to store values