17th Temple Conference
Friday, October 16, 2009
Plymouth Meeting DoubleTree Hotel
The future of biopharmaceutical statistics: A management view.
Raymond Bain and Steve Miola,
Merck & Company
Bruce Schneider and Cyrus Hoseyni,
Wyeth
Graphical displays of safety data in clinical trials.
Richard Heiberger, Temple University
Joseph Heyse, Merck, discussant
Multiple testing and false discovery rate.
Yoav Benjamini, Tel Aviv University
Sanat Sarkar, Temple University
Peter Westfall, Texas Tech University, discussant
Conference Schedule
8:15-9:00
Registration and Continental Breakfast
9:00-9:10
Introductory Remarks
Boris Iglewicz, Temple University
Session 1 The Future of Biopharmaceutical Statistics: A Management View.
9:10 - 9:45
Statisticians in the Pharmaceutical Industry: Challenges and Opportunities
for Leadership.
Bruce Schneider & Cyrus Hoseyni, Wyeth
9:45 – 10:20
Technical, Collaborative and Critical Thinking Skills in Quantitative
Scientists: A Biopharmaceutical Management Perspective on Need, Training
and Development
Raymond Bain & Steve Miola, Merck & Company
10:20 – 10:40
Break
10:40 – 11:20
Session 1 Discussion
Session 2 Graphical Displays of Safety Data in Clinical Trials.
11:20 – 11:55 Graphical Approaches to the
Analysis of Safety Data from Clinical Trials
Richard Heiberger, Temple University
11:55 – 12:10 Discussant
Joseph Heyse, Merck & Company
12:10-12:30 Session 2 discussion
12:30 – 2:00 Lunch
Session 3 Multiple Testing and False Discovery Rate
2:00 – 3:10
Recent Advances in Multiple Comparisons: What Error-Rate Will
Serve Your Goals?
Yoav Benjamini, Tel Aviv University & Sanat Sarkar, Temple University
3:10 – 3:25
Discussant
Peter Westfall, Texas Tech University
3:25 – 3:55
Session 3 discussion
3:55 – 4:00
Closing remarks
Abstracts
The future of biopharmaceutical statistics: A management view.
Statisticians in the Pharmaceutical Industry: Challenges
and Opportunities for Leadership
Bruce Schneider and Cyrus Hoseyni,
Wyeth Pharmaceuticals
Pharmaceutical industry continues to face unprecedented challenges in
its pursuit of discovery, development and marketing of new medicines:
higher regulatory and commercial hurdles, complex disease areas and unmet
needs, low rate of productivity and, the political environment just to
name a few. At the same time, the current environment presents
significant opportunities for the statisticians to play a critical role
in being part of the solution. In this talk we share the experiences
of senior leaders who have utilized their quantitative skills and statistical
thinking in conjunction with “acquired” soft skills to play
an influential role in leading and guiding the R&D organizations
and the decision-making process.
Technical, Collaborative and Critical Thinking Skills in Quantitative
Scientists: A Biopharmaceutical Management Perspective on Need,
Training and Development
Ray Bain and Steve Miola, Merck Research
Laboratories
The biopharmaceutical industry faces unprecedented challenges in the
treatment and prevention of human disease (e.g. declining success rate
in product development, rising R&D costs, growing reimbursement pressures
and greater scientific, regulatory and public scrutiny). But the opportunities
are also significant (e.g. rising disease incidence globally, high unmet
medical needs, new R&D technologies, and new emerging markets). The
goal of innovative R&D is to deliver therapies that provide true
value to patients while optimizing productivity, increasing probability
of success and decreasing cycle times.
Given these challenges and opportunities, there is an increasing need for professionally trained and continually developed quantitative scientists to address the current gap between the analytics demand and the supply of quantitative scientists. Statisticians are at the center of research design, evidence collection, analysis, interpretation and communication to meet the needs of multiple customers. A diverse set of ever-changing technical statistical skills is required throughout product discovery, pre-clinical development, clinical development and a product's post-approval promotion. But being technically competent is not enough. An effective statistical consultant role-model requires an interest and competency in collaboration (both internally and externally) and critical thinking skills.
Our talk will provide a management perspective on the training of statistical scientists including the development of curriculum guidelines, and fellowships and summer internships for graduate students in statistics. Continuing education and development will also be highlighted including the integration of personal development with performance, formal and informal practices to develop soft skills and preparing for the workforce of the future.
Graphical displays of safety data in clinical trials.
Graphical Approaches to the Analysis of Safety Data from Clinical
Trials
Richard M. Heiberger, Temple University
Patient safety has always been a primary focus in the development of
new pharmaceutical products. Safety issues in clinical trials are
usually reported in tables. Formal analysis of safety data is much
less developed than for efficacy data.
Safety data provides an ideal opportunity to use graphical methods to present concise summaries and communicate main messages. Graphs can be used in an exploratory setting to help identify emerging safety signals and in a confirmatory setting as a tool to elucidate known safety issues.
I spent a research leave year at GSK where I joined a company-wide team investigating graphical issues for display of clinical trial information. We developed several graphical displays for routine safety data collected during a clinical trial, covering a broad range of graphical techniques. The displays focus on key safety endpoints in clinical trials: the QT interval from electrocardiograms, laboratory measurements for detecting hepatotoxicity, and adverse events of special interest. We illustrate eleven specific graphical designs, many of which display the data along with statistics derived from them. We discuss in detail the statistical and graphical principles underlying the production and interpretation of the displays.
This talk is based on a paper coauthored with Ohad Amit and Peter W. Lane of GSK that appeared in 2008 in Pharmaceutical Statistics.
Multiple testing and false discovery rate.
Recent advances in multiple comparisons: what error-rate will
serve your goals?
Yoav Benjamini, Tel Aviv University and Sanat
Sarkar, Temple University
Research in the area of multiple comparisons has been flourishing in
recent years due to its increased relevance in modern scientific investigations.
As a result of this activity, many alternative ways to define and deal
with problems of simultaneous and selective inferences have been put
forward. In this talk, we shall present a wide variety of error-rates
that can be used to quantify the impact of multiplicity - familywise
error-rate (FWER), false discovery rate (FDR), k-FWER, k-FDR, positive
FDR, weighted FWER, weighted FDR, local FDR, and others - and briefly
discuss the appropriate methods to address them. Issues that an analyst
should consider when deciding an appropriate approach for the problem
being faced will also be presented. Finally, we shall discuss together
with the participants the matching of an error-rate to a problem, building
upon the participants' own experiences and the multiplicity problems
they face in practice.
Speakers
Raymond Bain Merck & Company
Ray Bain received his PhD from the Department of Statistics and Biometry,
Emory University School of Medicine in 1981. From 1981 to 1986
he was an Assistant Professor of Biometry, Medicine and Community Health
at Emory University and a member of the Georgia Center for Cancer Statistics. From
1986 to 1999, he was a member of The Biostatistics Center at George
Washington University where he was Co-Director of the Center and Research
Professor of Statistics. While at the Center he was a NIH-Sponsored
Coordinating Center Principle Investigator for multicenter clinical
trial programs in the areas of diabetes, maternal-fetal and neonatal
medicine, and prostatic disease. He joined Merck Research Laboratories
(MRL) in 1999 as Executive Director of the Clinical Biostatistics and
Research Decision Sciences (BARDS) organization with oversight for
the cardiovascular, infectious disease and neuroscience late drug development
programs. Since 2001, Dr. Bain has headed the Global BARDS organization
with responsibility for MRL Early and Late Development Statistics,
Epidemiology, Health Economic Statistics and Scientific Programming
groups. The Global BARDS organization develops and applies quantitative
scientific methods in the targeting, discovery, development, manufacturing
and commercialization of drugs and vaccines.
Yoav Benjamini Tel Aviv University
Yoav Benjamini (PhD Princeton ’81) is a professor of Statistics
at Tel Aviv University, where he also heads the statistical consulting
unit. His research is in the theory and applications of statistics, the
latter including biostatistics, genomics, functional brain imaging, computational
biology in behavior and meteorology. Together with Hochberg he initiated
the concept of the False Discovery Rate into multiple testing, and ever
since has been contributing to its development in theory and practice.
He serves on scientific advisory boards of public organizations in Israel
and recently finished a term as the president of the Israeli Statistical
Association.
Richard Heiberger, Temple University
Richard M. Heiberger is Professor of Statistics at Temple University.
He is coauthor of the graduate-level textbook 'Statistical Analysis
and Data Display: An Intermediate Course with Examples in S-Plus, R,
and SAS' (Springer, 2004) and the supplementary text 'R through Excel:
A Spreadsheet Interface for Statistics, Data Analysis, and Graphics'
(Springer, August 2009). He participated in the design of the
S-Plus and R linear model and analysis of variance functions while
on research leave at Bell Labs. He is the author of and contributor
to various R packages. His undergraduate degree in Mathematics is from
Oberlin College and his Ph.D. in Statistics is from Harvard University. He
is an Elected Fellow of the American Statistical Association (ASA)
and the Chair Elect of the ASA Section on Statistical Computing.
Joseph Heyse Merck
Dr. Heyse joined Merck Research Laboratories in 1976 as a statistician
supporting the Pre-clinical and Safety Assessment research programs.
In 1985 he was asked to provide statistical support to worldwide health
economic research programs being undertaken by the Company. This work
led to the establishment of a Health Economics Statistics Department
under Joe's direction in 1999. The Department has responsibility for
providing technical statistical and economic support to Merck research
programs in Quality of Life and Pharmacoeconomics. In 1994 Joe was given
additional responsibility for supporting statistical aspects of Phase
I-V clinical development programs for drug and vaccine projects for a
broad range of therapeutic areas. During this period Joe has had the
statistical oversight for the successful clinical development and regulatory
filings of more than 15 novel drug and vaccine products. He is currently
Vice President, Early Development Biostatistics and provides statistical
technical guidance to over 80 statisticians at the M.S. and Ph.D. level.
The group is currently collaborating on research supporting drug and
vaccine discovery, early clinical development, biomarker qualification
and application, molecular profiling, and investigational research.
Academically, Joe received B.S. and M.S. degrees in Mathematics at Villanova University, an MBA from Temple University, and a Ph.D. in Statistics, also from Temple. His research interests are in economic evaluations of health care and statistical methods for multiple comparisons/multiple endpoints, and longitudinal data models. He has more than 80 publications in statistical and subject-matter journals.
He was elected Fellow of the American Statistical Association in 1997.
Cyrus Hoseyni Wyeth
Cyrus Hoseyni is Vice President of Global Biostatistics & Programming
and Chief Statistician for Wyeth Pharmaceuticals. Prior to joining
Wyeth, Cyrus held the position of Executive Director & Site Head
of Biostatistics & Reporting, Pfizer Global Research & Development. He
has over 20 years of experience in the pharmaceutical industry, assuming
roles of increasing responsibilities from project statistician (pre-clinical
and clinical) to leading global organizations. He has extensive
experience in directing statistical and regulatory aspects of developing
new medicines and a strong track record for establishing statistical
organizations recognized for statistical leadership, influence, innovation,
and competency at all levels. He is a member of Wyeth’s
Medical Executive Committee and co-chair of the Clinical Review Committee. His
academic background consists of a Ph.D. in Biostatistics with emphasis
on cancer research and quantitative risk assessment, and Master’s
degrees in Mathematics & Economics from the University of Southern
California. His professional activities have included serving
as a member of PhRMA’s Biostatistics & Data Management Technical
Group for three years and serving as program and workshop chair for several
Biopharmaceutical Statistics meetings.
Steve Miola, Merck & Company
Steve Miola received his PhD from the Department of Biometrics, Temple
University School of Medicine in 1979. He joined Merck & Co. in
1977 as a biostatistician and held positions of increasing responsibility
in the Department of Biostatistics and Research Decision Sciences (BARDS)
organization. He was awarded a Henry W. Gadsden Fellowship from the
Company in 1986 to improve the collaboration between Marketing and
Research during the New Drug Application process. He later joined the
Human Health Division and was named Director of Innovative Media, Department
of Marketing Communications in 1994. In that capacity he was
responsible for all electronic communications between US field-based
representatives and health care providers, and the development of the
Internet as a channel of communication for all of Merck's US-promoted
products. In 2003 he rejoined the BARDS organization with responsibility
to lead the Department's effort to train and develop its talent.
Sanat Sarkar Temple University
Dr. Sanat K. Sarkar, Professor and Senior Research Fellow in the Department
of Statistics, Temple University, has received his PhD in Statistics
from Calcutta University in 1982. Dr. Sarkar has made some fundamental
contributions to the development of multiple testing. His research has
been funded by NSF (National Science Foundation) and NSA (National Security
Agency), and often been cited in peer-reviewed journals. He has delivered
invited talks at numerous national and international conferences. Dr.
Sarkar has co-organized a major conference on Multiple Comparisons funded
by the NSF and served on the organizing committees of several international
conferences on the same topic. He is on the editorial boards of the
American Statistician and Sankhya. He has supervised 17 Ph.D. dissertations. Dr.
Sarkar has been recognized as a fellow by both the Institute of Mathematical
Statistics and the American Statistical Association, and as an elected
member of the International Statistical Institute. He was awarded the
Musser Award for excellence in research by the Fox School, and inducted
several times to the Dean’s Research Honor Roll.
Bruce Schneider Wyeth
Bruce Schneider is Executive Vice President and Chief of Operations for
Wyeth Research. He has spent his entire career at Wyeth in a
variety of technical and general management roles. He initially
progressed from Manager, Biostatistics through a series of positions
to Vice President, Clinical Operations with responsibility for worldwide
data management, clinical programming, biostatistics, clinical writing
and field monitoring. He then moved into a broader R&D role
with responsibility for Wyeth’s drug development operating model
(strategy, teams, systems and governance), its portfolio management
system, interactions with co-development partners and organization-wide
business improvement programs. He also has oversight responsibility
for the multi-billion R&D budget and a variety of administrative
support functions. He has a deep understanding of regulatory
processes around the world with special expertise and responsibilities
for R&D efforts in Japan. He is a member of Wyeth’s
R&D and Pharmaceutical Executive Management Teams. His academic
background consists of a bachelor's degree in applied mathematics from
Brown University and a doctorate in applied statistics from Temple
University. He has been involved in PhRMA and its predecessor
organization, ultimately serving as chair of its Biostatistics Subsection,
is a member of numerous professional societies and has received several
awards for outstanding contributions at Wyeth and in the community.
Peter Westfall Texas Tech University
Peter Westfall (Ph.D. UC-Davis, 1983) is Paul Whitfield Horn Professor
of Statistics and James Niver Professor of Information Systems and
Quantitative Sciences at Texas Tech University. He has consulted
with various pharmaceutical companies for 20 years, and has published
over 100 articles and three books on statistical theory and practice. Using
funds from a grant from the Pharmaceutical Manufacturers’ Association,
he developed the SAS/STAT® procedure PROC MULTTEST, which
performs resampling-based multiple testing adjustments; using funds
from another recent grant from a private pharmaceutical company, he
developed a publically available clinical trials simulation system
(http://www.biopharmnet.com/innovation/trial_simulation/cts1.php)
that can be used to design studies optimally. Peter is past editor
of The American Statistician, a Fellow of the American Statistical
Association, and a Fellow of the American Association for the Advancement
of Science.
Registration
Charges:
General - $100
Merck & Wyeth- $70
Full time graduate students - $30
Registration includes: Continental Breakfast, Lunch, Break, Parking.
Registration:
Registration and web information will start on September 1, 2009. Please
send check (Made out to Temple University (Biost)), email address,
and company name to:
Boris Iglewicz, Director,
Biostatistics Research Center,
Department of Statistics, Temple University 006-12,
1810 N. 13th Street,
Philadelphia, PA 19122-6083
For additional information, contact Boris Iglewicz, Director, email: borisi@temple.edu or telephone (215) 204-8637.
Directions
DOUBLE TREE GUEST SUITES, PLYMOUTH MEETING
640 W. Germantown Pike, Plymouth Meeting PA 19462
(610) 834-8300
From Airport: Take 95 South to 476 North to the last exit #20(Germantown Pike-West). Merge with Germantown Pike and follow for 3 lights. Make a right onto Hickory Rd. at the 3rd light. The hotel is the 3rd building on the left.
New York/ New Jersey Turnpike: Take the New Jersey Turnpike to exit #6, which is PA turnpike. Go west to exit #333- Norristown. Follow signs to Plymouth Rd. Go to the 1st light and make a left. Go to the next light and make a right onto Germantown Pike. Go to the second light and make a right on Hickory Rd. The hotel is the second driveway on the left.
Washington D.C., Wilmington, and Delaware: Take I-95 North to Route 476 North. Take Route 476 to the Germantown Pike West exit #20. Go to the third light, Hickory Rd., and make a right. The hotel is the 2nd driveway on the left.
Route 476: Take 476 to the Germantown Pike West exit #20. Go to the third light, Hickory Rd., and make a right. The hotel is the 2nd driveway on the left.
From downtown Philadelphia: I-76 west Plymouth Meeting exit #331B (Route 476). Take Route 476 north to Germantown Pike exit. Go to the third light, Hickory Rd., and make a right. The hotel is the 2nd driveway on the left.