|
Begins
16th March 2012
Aim of Course: This 3-week course is intended to
cover the fundamental
techniques in combining data
from multiple studies using
R. The course will cover the
methods of fixed-effects and
random-effects meta-analysis
models as well as the
techniques in identifying
publication bias. R packages
"rmeta" and
"meta" will be
introduced for the
step-by-step implementation
with "forest" and
"funnel" plots.
Who Should Take This Course: Anyone who wishes to conduct
meta-analysis methodology
and step-by-step
implementation of these
methods in R. Class
participants are encouraged
to bring their own datasets
and ongoing projects into
the class to be used as
examples.
Instructor:
Din Chen received his Ph.D. in
Statistics from the
University of Guelph
(Canada) in 1995 and is now
a professor in biostatistics
at the University of
Rochester Medical Center.
Professor Chen was
the Karl E. Peace endowed
eminent scholar chair and
Professor in biostatistics
for the Jiann-Ping Hsu
College of Public Health at
the Georgia Southern
University. He consults on a
regular basis for
biopharmaceutical firms and
government agencies and has
extensive expertise in
clinical trials,
bioinformatics and
statistics applications.
More than 80 refereed
professional publications of
his are in print. He is
co-author of "Clinical
Trial Methodology" and
"Clinical Trial Data
Analysis Using R"
published by CRC in 2010
Prerequisite:
Course participants should
have a basic understanding
of R (equivalent to "Introduction
to R"), though,
regardless, the instructor
will guide you in the
learning process. Basics in
statistics, estimation and
hypothesis testing are also
expected.
Organization
of the Course: The course takes place over the Internet. Course participants
will be given access to a
private bulletin board, on
which they will receive
course materials. The board
will also serve as a forum
for discussion of ideas and
problem solving. R software
can be downloaded free and
you'll be given step-by-step
instructions in its use.
Text
Book: Din Chen and Karl E. Peace (2010). Clinical
Trial Data Analysis Using R.
Chapman & Hall / CRC
Biostatistics Series.
(Chapter 8 with additional handouts)
Course Program: The course is structured as
follows
Session 1 - Fixed-Effects
Meta-Analysis
- Data structure for meta-analysis
(Section 8.1)
- Fixed-effects model with binomial
outcome measures
(Section 8.2)
- Fixed-effects model with
continuous outcome
measures (Section 8.2)
- R packages "rmeta" and
"meta" for
fixed-effects
meta-analysis (Section
8.3)
Session 2 - Random-Effects
Meta-Analysis
- Why
random-effects model
- Random-effects model with binomial
outcome measures
(Section 8.2)
- Random-effects model with
continuous outcome
measures (Section 8.2)
- R packages "rmeta" and
"meta" for
random-effects
meta-analysis (Section
8.3)
Session 3 - Publication Bias
- Pros and cons in meta-analysis
- Participant-submitted examples
- Indentify publication bias with
"funnel" plot
and "metabias"
test
Cost:
$299
per participant. Early-bird
discount may apply. Students,
faculty and research workers
at academic institutions are
eligible for a further
discount. Just send an email
from your academic or
institutional email account
to courses@statcourse.com
to receive a discount coupon
worth $35 toward the cost of
the course.
Immediately
after your payment is
credited, you will receive
an email giving you sign up
instructions, and the web
address (URL) of the course
material. Note that
you will not be able to
access this address until
the start date of the
course. We recognize
that most course
participants have full time
jobs. A charge of $50 is
made for refunds up until
one week prior to the start
of the course. While
no refunds are given after
this date, participants may
retake the course without
charge the
next time the course is
offered. |
