R, clinical trials and the FDA

On Sun, Jan 11, 2009 at 11:05 AM, Kingsford Jones
<kingsfordjones at gmail.com> wrote:

I hope that Marc doesn't mind, but I felt that part of his recent post
was important enough to deserve it's own subject line rather then
being lost in a 60-msg-long thread...

I also wanted to thank Marc for this wealth of information on using R
in clinical trials. I particularly want to recommend the "R:
Regulatory Compliance and Validation Issues" document at
http://www.r-project.org/certification.html .  Even if you're not
looking to validate R for 21CFR11 compliance, this document is an
excellent description of R's world-class software development process.
 With this, and the documented use of R by the FDA itself and within
pharma companies for clinical trials, I hope we can settle the "Is R
Validated?" question at long last. Thanks go to the authors (Marc
Schwartz, Frank Harrell, Tony Rossini and Ian Francis) and the R
Foundation generally for putting this together.

Thanks kindly David.

On the R Foundation side, I want to ensure appropriate credit and note
the tremendous assistance specifically provided by Doug Bates, Martin
Maechler, Peter Dalgaard, Kurt Hornik and John Fox. Over the past couple
of years their time, support, review and edits of the document ensured
that the "light at the end of the tunnel" was not an oncoming train and
ensured the accuracy of the content in documenting the R development
process.

In addition, their critical facilitation of the R Foundation review and
approval process has enabled us to have these recent discussions
predicated upon a base of formal and publicly available information that
should put to rest any concerns over R's quality development procedures.

R is developed and maintained using a world class process, implemented
by a world class team. Importantly and so that we never forget, that
Core team is comprised of volunteers who have donated of their time and
careers to bring us R and to enable this wonderful community.

Regards,

Marc