Missing Data Workshop Announcement & Call for Presentations

[David B. Rosen]

This is the first announcement and call for presentations for:

                       MISSING DATA: METHODS AND MODELS
                              A NIPS*95 Workshop
                           Friday, December 1, 1995

INTRODUCTION

Incomplete or missing data, typically unobserved or unavailable features in
supervised learning, is an important problem often encountered in real-world
data sets and applications. Assumptions about the missing-data mechanism are
often not stated explicitly, for example independence between this mechanism
and the values of the (missing or other) features themselves. In the important
case of incomplete training data, one often discards incomplete rows or columns
of the data matrix, throwing out some useful information along with the missing
data. Ad hoc or univariate methods such as imputing the mean or mode are
dangerous as they can sometimes give much worse results than simple discarding.
Overcoming the problem of missing data often requires that we model not just
the dependence of the output on the inputs, but the inputs among themselves as
well.

THE WORKSHOP

This one-day workshop should provide a valuable opportunity to share and
discuss methods and models used for missing data. There will be a number of
short presentations, with discussion following each and continuing in greater
depth after all are done. Particular classes of methods we hope will be
discussed include:

   * Discarding data, univariate imputation (filling-in) of missing values,
     etc.
   * Single and multiple imputation based on other (non-missing) features.
   * Mixture models for the joint (input-output) space.
   * EM algorithm.
   * Recurrent networks, iterative relaxation, auto-associative pattern
     completion.
   * Methods specific to certain learning algorithms, e.g. trees, graphical
     models
   * Stochastic simulation and Bayesian posterior sampling

Presenters so far include (alphabetically) Leo Breiman (tentative!), Zoubin
Ghahramani, Bo Thiesson / Steffen Lauritzen (missing data in graphical models),
and Volker Tresp.

CALL FOR PRESENTATIONS

Additional speakers are needed to present some of the methods mentioned above,
or other topics of interest. If you would like to do so, or if you have
additional suggestions to offer, please contact us as soon as possible.

ORGANIZERS

Harry Burke <burke at unr.edu>
David Rosen <rosen at unr.edu>
New York Medical College, Department of Medicine, Valhalla NY 10595 USA
FAX: +1.914.347.2419
 
FURTHER INFORMATION

Check the workshop's Web page (the above is a snapshot of it)
           http://www.scs.unr.edu/~cbmr/nips/workshop-missing.html
for further updates over time.  It also has a link to the NIPS*95 home page.

Those without direct access to the World Wide Web can use Agora, the
email-based Web browser.  Send the message HELP, or the message
         send http://www.scs.unr.edu/~cbmr/nips/workshop-missing.html
to agora at www.undp.org .  Any Subject header is ignored.

--
David Rosen <rosen at unr.edu>
New York Medical College