A library for cause-effect relationships.

Latest on Hackage:

This package is not currently in any snapshots. If you're interested in using it, we recommend adding it to Stackage Nightly. Doing so will make builds more reliable, and allow to host generated Haddocks.

BSD3 licensed and maintained by Benjamin Weber

Pareto: Is a pareto distribution present?


  • The main function pareto will return True if a pareto distribution is present.
  • causesMaxConcentration returns the causes with the maximum concentration (rank * value).
  • effectsMaxConcentration returns the effects with the maximum concentration.
  • If you want the effects for a specific share of causes, use effects.
  • You get the causes for a specific share of effects via causes.


  • pareto employs an entropy model. If entropy for a list of numbers falls below a controlLimit, pareto distribution is present.
  • causesMaxConcentration and effectsMaxConcentration will return the respective share of the causes and effects where concentration (rank * value) is highest.


Examples can be found in the package's documentation.


Revision history for pareto -- 2016-10-17

  • First version. Main functions: pareto, causes, effetcts, causesMaxConcentration, effectsMaxConcentration. -- 2016-10-19

  • Second version. Fixes critical bug: entropy calculation has been wrong.
Depends on 1 package:
Used by 1 package:
comments powered byDisqus