Re: Ordinal-Interval Correlation

Ray Koopman wrote:

The "basic assumptions" are that L|X is normal and homoscedastic.

Thanks Ray. So it sounds like L has a mixture-of-two-normals
distribution.
--
John Uebersax PhD

.

References:
- Re: Ordinal-Interval Correlation
  - From: Jeff Miller
- Re: Ordinal-Interval Correlation
  - From: Richard Ulrich
- Re: Ordinal-Interval Correlation
  - From: John Uebersax
- Re: Ordinal-Interval Correlation
  - From: Ray Koopman

Relevant Pages

Re: ci on radius
... Ray Koopman wrote: ... distribution being at the origin? ... u = the unknown true mean vector of. ... Then the 100c% confidence region for u is ...
(sci.stat.math)
Re: change in rank versus change in continuous variable
... Ray Koopman wrote: ... but it fact it is stronger that the usual correlational ... because both of your variables -- change in brain size ... John Uebersax PhD ...
(sci.stat.consult)
Re: Is there a statistical test for comparing two sets of values (which are statistics)?
... Ray Koopman wrote: ... distribution for r here is normal? ... Strictly speaking, yes. ... that the nominal p-values from the t-test are not so different from ...
(sci.math)
Re: Uniform distribution on a hyperannulus
... Ray Koopman wrote: ... is the cdf of a chi-square variable with n degrees of freedom. ... are the coordinates of a point whose distribution is uniform on the ...
(sci.math)