skills can be developed at the FDA through great mentoring and
What are the motivations to work as a statistician for the FDA?
other educational opportunities, both statistical and otherwise. A
The work is never dull, and there are always new things to learn.
good way to characterize the skills of an experienced FDA statisti-
Statisticians see the newest medical breakthroughs and the ‘real-
cian is as generalist, specialist, regulatory reviewer, regulatory sta-
world’ application of statistical theory and methodology. There is
tistical researcher, educator, trainer and mentor, collaborator in a
usually exposure to many submissions. Preparation of the data is the
multidisciplinary team, leader, communicator, writer, and negotia-
responsibility of the company, but FDA statisticians have access to it
tor. Career advancement is possible not only through management,
and the ability to evaluate and reanalyze studies, so the environment
but also statistical scientific leadership, as FDA values such talent.
is very data rich. There is, however, one caveat: Most of the data
FDA needs statistical expertise for many of its more than 40
belong to the sponsors who conducted the trials and cannot be used
subject-matter advisory committees and panels that provide inde-
in public presentations or publications by FDA personnel without
pendent advice from outside experts on issues related to human
permission. FDA open advisory committee meetings do, however,
and veterinary drugs, medical devices, biological products, and
provide an opportunity for some aspects to be made public.
food. Each advisory committee consists of a chair and several
Another advantage for statisticians working for the FDA is flex-
members with specialized expertise, augmented by nonvoting
ibility in working hours and work place. Similar to all government
consumer and industry (and sometimes patient) representatives.
agencies, it is a family-friendly work environment. FDA's new state-
For many FDA advisory committees, there is at least one expert
of-the-art campus in White Oak, Maryland, which is partly com-
statistician. An expert can be nominated by a professional soci-
pleted, will eventually consolidate the FDA’s three centers.
ety, the individual, or other interested persons. These committees
FDA is currently hiring statisticians to meet new challenges in
deliberate in public to make recommendations to FDA. (Often
medical product evaluation (including drugs, devices, vaccines,
the considerations regard the approvability of a particular medical
blood products, diagnostics), quantitative safety assessment, person-
product.) For the consideration of such a product, statisticians for
alized medicine and genomics, quality by design in product manu-
the company and the FDA usually make presentations, and then
facturing and monitoring, post-approval, and epidemiological/sta-
the committee discusses the issues in public and makes recom-
tistical skills to track life cycle product safety and efficacy. Many of
mendations to the agency. Frequently, these presentations and the
these areas have been highlighted by FDA’s Critical Path Initiative.
subsequent discussion involve statistically challenging and high-
FDA statisticians also are active in statistical regulatory research.
impact issues in clinical trials and methodology. Although the
The availability of scientific computing tools and data storage/
committees are advisory in nature to the agency, final decisions
access/retrieval systems and electronic database linkage are open-
by FDA usually pay close attention to the recommendations of
ing ways to do regulatory research, data mining, and drug safety
the committees.
surveillance that could only have been imagined a few years ago. As
the nation prepares to integrate more of its health records for better
What Else Do FDA Statisticians Do?
outcome surveillance and global drug development increases with
Statisticians at FDA are active in the larger statistical community. clinical research being conducted in new regions of the world, the
There is an internal organization called the FDA Statistical experimental study design challenges increase, as do the analysis and
Association (FDASA) that coordinates statistical activities across visual displays of information needed to ensure quality of inferences
the FDA centers. FDASA partners with the Biopharmaceutical and decisions based upon these source of evidence.
Section to plan the very successful FDA/Industry Statistical Legislation for FDA in 2007, which established the Reagan-
Workshop, which occurs every September in the greater Udall Foundation (an entity not unlike the NIH Foundation), has
Washington, DC, area. Some FDA statisticians serve as adjunct afforded new opportunities for statisticians. Its purpose is to advance
faculty for various universities. FDA statisticians are involved in the mission of FDA to modernize medical, veterinary, food, food
planning and attending statistical conferences and workshops ingredient, and cosmetic product development; accelerate innova-
with DIA (used to stand for Drug Information Association), tion; and enhance product safety. It is to take into consideration
the Pharmaceutical Research and Manufacturing Association the Critical Path reports and priorities; identify unmet needs in the
(PhRMA), and Advanced Medical Technology Association development, manufacture, and evaluation of the safety and effec-
(Advamed). Initiated by statisticians at the FDA and in industry, tiveness—including post-approval—of devices, diagnostics, biolog-
an ASA special-interest group for medical devices and diagnostics ics, and drugs; and the safety of food, food ingredients, and cos-
(SIGMEDD) was recently established. metics, including the incorporation of more sensitive and predictive
FDA statisticians have written guidances that affect the industry tools and devices to measure safety. The foundation is to identify
and global medical product development. In addition, there is a existing and propose federal intramural and extramural research and
guidance for establishing and operating a clinical trial data moni- development programs relating to the above goals and priorities. It
toring committee, a statistical guidance document on reporting will be an important vehicle for private and public stakeholders to
the results of diagnostic tests, and a draft document on the use of collaborate to address these priorities and opportunities.
Bayesian statistics in medical device clinical trials. Statisticians at Another exciting initiative that will potentially affect and provide
FDA are taking the lead now to develop new guidance documents opportunities to the statistical community is the FDA fellowship
about statistically challenging areas such as noninferiority study program. The fellowship program is in the process of development
designs, adaptive study designs, missing data in clinical studies, sta- and will be advertised some time in the near future.
tistical multiplicities associated with multiple clinical endpoints and For all these reasons, we believe FDA is a great place for stimulat-
desired claims, good practice for microarray and predictive signa- ing statistical activity. To learn more about the topics mentioned in
tures, and meta-analysis in rare safety outcomes. this column, visit the FDA at www.fda.gov. n
OCTOBER 2008 AMSTAT NEWS 3
Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53  |  Page 54  |  Page 55  |  Page 56  |  Page 57  |  Page 58  |  Page 59  |  Page 60  |  Page 61  |  Page 62  |  Page 63  |  Page 64  |  Page 65  |  Page 66  |  Page 67  |  Page 68  |  Page 69  |  Page 70  |  Page 71  |  Page 72  |  Page 73  |  Page 74  |  Page 75  |  Page 76  |  Page 77  |  Page 78  |  Page 79  |  Page 80  |  Page 81  |  Page 82  |  Page 83  |  Page 84  |  Page 85  |  Page 86  |  Page 87  |  Page 88  |  Page 89  |  Page 90  |  Page 91  |  Page 92