On 28 Oct 2000 03:53:43 -0700, [EMAIL PROTECTED] (Donald Burrill)
wrote:
> On 27 Oct 2000, Dr. S. Shapiro wrote:
>
> > I have quantified experimentally the activity ("X") of a
> > half-dozen different products (A-F). These 6 commercial
> > products all contain the same "active ingredient" over a
> > range of different concentrations (and a couple of products
> > share the same "active ingredient" concentration). The
> > problem arises from the fact that these 6 commercial
> > preparations each contain different additives that may
> > possibly impact on the observed activity, and no two
> > products contain identical sets of additives.
> > Under these circumstances, is there a statistical procedure
> > that wouldenable me to distinguish the effect of the
> > "active ingredient" per se from the mitigating effects
> > (either positive or negative) of the additives?
Don >
> Under the conditions you describe, the short answer is "No".
>
The conditions do seem to imply there is a lot of noise in the
analysis. However,
- if the noise is hypothetical, and
- the various additives happen to have absolutely no effect, and
- the active ingredient has a strong, simple, linear effect --
then you might be able to attribute the effect to the active
ingredient.
--
Rich Ulrich, [EMAIL PROTECTED]
http://www.pitt.edu/~wpilib/index.html
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
