ranking subjective data for non-parametric analysis

Home > Statistics Every Writer Should Know > The Stats Board > Discusssion

ranking subjective data for non-parametric analysis
Message posted by brad on October 9, 1999 at 12:00 AM (ET)

Is it OK to subjectively rank some attribute in a series of images for analysis with the Wicoxon Rank Sum Test? Or is it necessary to first create a scoring system for measuring the attribute and then ranking the scores for analysis by the Wicoxon Rank Sum Test?

READERS RESPOND:
(In chronological order. Most recent at the bottom.)

Re: ranking subjective data for non-parametric analysis
Message posted by Bill on October 10, 1999 at 12:00 AM (ET)

It depends on what you are trying to accomplish. But, if the intent is to conduct a rigorous study that can be replicated then you need to develop a system for measuring the attribute.

Your $5 contribution helps cover part the $500 annual cost of keeping this site online.