MathGroup Archive 2005

[Date Index] [Thread Index] [Author Index]

Search the Archive

Re: Skewness problem

  • To: mathgroup at smc.vnet.net
  • Subject: [mg63002] Re: Skewness problem
  • From: Bill Rowe <readnewsciv at earthlink.net>
  • Date: Sat, 10 Dec 2005 06:03:24 -0500 (EST)
  • Sender: owner-wri-mathgroup at wolfram.com

On 12/9/05 at 5:10 AM, Karl_boehme_9 at msn.com (Klaus G.) wrote:

>Skewness[ {0, 7, 7, 6, 6, 6, 5, 5, 4, 1}] results in -1.04137.

>Reversing the data to {1,4,5...} I expected a different skewness,
>because the "tails" are reversed. But again I get -1.04137. Is
>there an error in reasoning?

Yes, there is an error in your reasoning. The left most tail is determined by the smallest values in the sample set and the right most tail is determined by the largest values in the sample set. Since the magnitude of any value in the data set is independent of its position within the set, it should be clear skewness of the data set must also be independent of order within the set.

--
To reply via email subtract one hundred and four


  • Prev by Date: Re: Skewness problem
  • Next by Date: A more syntactically compact way?
  • Previous by thread: Re: Skewness problem
  • Next by thread: Re: Skewness problem