Welcome, Guest

value composite rank (VC1, VC2 and/or custom)
(1 viewing) (1) Guest
  • Page:
  • 1
  • 2

TOPIC: value composite rank (VC1, VC2 and/or custom)

Re: value composite rank (VC1, VC2 and/or custom) 3 months, 3 weeks ago #1887

Normalise the values to 0-1 by using the MIN and MAX values you find for each factor, so that the distribution is always more or less normal - i.e. the big hump is in the middle, and not too far to one side or the other. You can use the histogram to show you the distribution.
Thorunn
  • Page:
  • 1
  • 2
Time to create page: 0.09 seconds