On Tue, 11 Jul 2000, Znarf Akfak wrote:
> In article [EMAIL PROTECTED] (Donald Burrill) wrote:
>
> > To whom, for what purpose(s) ? The "several bivariate associations"
> > part rather suggests that you'll want to be making comparisons,
> > implicitly if not explicitly; and even if you don't, readers will.
>
> We want to report the correlation between two methods of measurement
> for about 20-30 different response variables. It isn't expected that
> the methods will give the same individual or average values, but the
> degree of linear correlation is useful in future large studies to make
> adjustments for using the less costly method. Sample size is about
> 100-150.
Sounds like a prediction or calibration kind of problem. As Joe Ward
pointed out, raw regression coefficients, and standard errors of
measurement, are more stable than correlation coefficients.
> > (For example, are all the variables in question equivalently (in any
> > sense!) restricted in range?)
>
> The variable values aren't restricted in range, and the associations
> are approximately linear for most of the variables.
That you have not imposed artificial restrictions on the range of the
variables does not imply that their range is not restricted. After all,
you were asking about bivariate normality with respect to a (presumably)
real (and therefore finite) data set. There may be natural constraints
on their range(s).
-- DFB.
------------------------------------------------------------------------
Donald F. Burrill [EMAIL PROTECTED]
348 Hyde Hall, Plymouth State College, [EMAIL PROTECTED]
MSC #29, Plymouth, NH 03264 603-535-2597
184 Nashua Road, Bedford, NH 03110 603-471-7128
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
