On line registration is now closed , please
register on site.
Registration Fee is $100CDN. However, for students, postdoctoral fellows
and invited speakers there is no fee.
Format:
Two days of invited lectures and contributed papers prior to the Joint
Statistical Meetings
Overview:
Modern data often includes some form of censorship or missing data.
Data imputation is a critical component of the analysis of such data
and crude methods for data imputation can lead to substantial bias in
the results and the conclusions. Missing data problems are common in
health research (e.g. retrospective and prospective studies), sample
surveys (e.g. nonresponse), and less obvious parts of any study in which
the data available is influenced by what is easy or feasible to collect.
Longitudinal studies which collect data on a set of subjects repeatedly
over time are subject to attrition, Subjects drop out because they move,
suffer side effects from drugs, or for other often unknown reasons.
Similarly in sampling, survey “nonrespondents” are often ignored,
although factors related to the objectives of the study such as income
may influence the completeness of a subjects response.
Problems which involved missing data have historically been dealt with
using a “complete-case analysis'' which ignores the missing data
and therefore biases conclusions. There have been many new computationally
intensive tools developed in recent years which can be applied to these
problems: likelihood and estimating function methodology, cross-validation,
the bootstrap and other simulation techniques, Bayes' and multiple imputation,
and the EM algorithm.
The primary goal of the workshop is to provide impetus to the development
of mathematical and statistical tools for the analysis of data under
various patterns of censorship and mechanisms governing missingness
and data imputation. The workshop will be of interest to researchers
and graduate students in many different disciplines, including biostatistics
and sampling theory.
Preliminary list of Speakers
N. Breslow (Washington)
S. Bull (Toronto)
N. Chatterjee (NIH)
Jinbo Chen (NIH)
R. J. Cook (Waterloo)
J.D. Kalbfleisch (Michigan)
J.F. Lawless (Waterloo)
R.J.A. Little (Michigan)
D. L. McLeish (Waterloo)
A. Rotnitzky (Harvard)
D.B. Rubin (Harvard)
D. Sharfstein (Johns Hopkins)
A. Scott (Auckland)
C. A. Struthers (Waterloo)
M. E. Thompson (Waterloo)
C. Wild (Auckland)
G. Y. Yi (Waterloo)
Plus contributed sessions -
To submit
an abstract for invited or contributed talks (deadline June 15, 2004)
Travel support
Funding support is available to cover part of the travel expenses of
graduate students. If you would like to apply for a travel funds please:
1) Register for the workshop
2) Submit an abstract before June 15, 04 if you would like to give a
talk
3) Copy the text below, provide responses, and send the following information
to the organizers to Funding
Request with "Missing Data Workshop" in the subject line.
(or rjcook@uwaterloo.ca and
dlmcleis@uwaterloo.ca)
a) Name, Institution and Graduate Program
b) Email
c) Reason for attending the workshop
d) Anticipated costs for travel and accomodation.
e) Are you planning on giving a talk?
f) Supervisor, Graduate Advisor, or other reference: Name, Telephone
Number or E-mail Address
(Please have your reference send an email in support of this application
to the workshop organizers by email indicating your research topic.)
Mailing List
To receive updates on activities at Fields please subscribe to our mailing
list at
www.fields.utoronto.ca/maillist
Back to top
The
National Program on 