Back to the Top
The following message was posted to: PharmPK
On Feb 9, 2008 9:09 PM, Davewrote:
> While I was looking for a quick, easy, and free way of running the
> typical bioequivalence ANOVA, I stumbled upon the following very
> useful post:
> http://finzi.psych.upenn.edu/R/Rhelp02a/archive/16552.html
> "R", similar to S and S+, is an open source statistical package that
> has gained much utility in academia (and industry), although it
> promises no validation or guarantees whatsoever.
Neither does any other statistical package. R isn't different than
SAS, S-PLUS, etc, in that respect. There is no reason that if
proper
Validation is such a misused term. The only thing it refers to
legally in the context of a health authority submission is conifidence
in a specific purpose (predicate docs for a health authority), which a
software vendor can't fully provide.
And while sometimes it is used to describe "verification", there is
much confusion in what that actually means. People often use that
term in an informal sense rather than in the formal sense in the
domain of "computer systems validation" (which is about more things
than validation, but again, lots of specific annoying defintions).
best,
-tony
blindglobe.-at-.gmail.com
Muttenz, Switzerland.
Want to post a follow-up message on this topic?
If this link does not work with your browser send a follow-up message to PharmPK@boomer.org with "Validated statistical software" as the subject | Support PharmPK by using the |
Copyright 1995-2011 David W. A. Bourne (david@boomer.org)