Re: ordianal data - normal distribution
- From: Richard Ulrich <Rich.Ulrich@xxxxxxxxxxx>
- Date: Thu, 01 Mar 2007 00:03:00 -0500
On Tue, 27 Feb 2007 12:27:02 +0100, Carmen Meier <carmei3@xxxxxx>
wrote:
Hi to all
Is ist possible to calculate a normal distribution for ordinal data?
f.e -10;-20;-40;-70;75;55;22;8
And if yes, what`s the best test for it?
The two parameters for a normal distribution are the mean
and variance.
The best general test for normality these days seems to be
the Shapiro-Wilks W. It can be used for small samples,
though there will not be much power with small N.
Is "normality" what you wanted to test?
--
Rich Ulrich, wpilib@xxxxxxxx
http://www.pitt.edu/~wpilib/index.html
.
- Follow-Ups:
- Re: ordianal data - normal distribution
- From: Bruce Weaver
- Re: ordianal data - normal distribution
- From: Carmen Meier
- Re: ordianal data - normal distribution
- Prev by Date: Call for Papers with Extended Deadline: 2007 International Conference on e-Learning, e-Business, Enterprise Information Systems, and e-Government (EEE'07), June 25-28, 2007, USA
- Next by Date: Re: ordianal data - normal distribution
- Previous by thread: Call for Papers with Extended Deadline: 2007 International Conference on e-Learning, e-Business, Enterprise Information Systems, and e-Government (EEE'07), June 25-28, 2007, USA
- Next by thread: Re: ordianal data - normal distribution
- Index(es):
Relevant Pages
|
