Opened 11 years ago

Closed 11 years ago

Last modified 10 years ago

#879 closed defect (invalid)

Calculation of Theil's inequality coefficient U2 should be based on relative errors instead of absolute errors

Reported by: gkronber Owned by: gkronber
Priority: lowest Milestone: HeuristicLab 3.3.0
Component: ZZZ OBSOLETE: Modeling Version: 3.3
Keywords: Cc:

Description


Change History (8)

comment:1 Changed 11 years ago by gkronber

  • Status changed from new to assigned

comment:2 Changed 11 years ago by gkronber

Fixed with r2827.

comment:3 Changed 11 years ago by gkronber

Fixed division by zero in relative error calculation for Theil's U with r2828.

comment:4 Changed 11 years ago by gkronber

Actually it depends on the nature of the original variable. If the values are already a differential symbol we should use the actual values instead of changes. Maybe it's best to calculate both values and let the user decide which one is more interesting.

comment:5 Changed 11 years ago by gkronber

  • Status changed from assigned to new
  • Version changed from 3.2 to 3.3

comment:6 Changed 11 years ago by gkronber

  • Resolution set to invalid
  • Status changed from new to closed

Actually after consulting the original sources this is not necessary.

Last edited 11 years ago by gkronber (previous) (diff)

comment:7 Changed 10 years ago by swagner

  • Milestone changed from Iteration 4 to Current

Milestone Iteration 4 deleted

comment:11 Changed 10 years ago by swagner

  • Milestone changed from Current to HeuristicLab 3.3.0

Milestone Current deleted

Note: See TracTickets for help on using tickets.