Seminar
Statistical Laboratory
Iowa State
University
DATE AND TIME: Monday, November 14, 2005, 4:10
p.m.
PLACE: 319 Snedecor
SPEAKER:
Paul Speckman, Department of Statistics, University of
Missouri-Columbia
TITLE: Spatially Adaptive Smoothing
Splines
ABSTRACT
Smoothing splines and more
generally penalized smoothing methods are popular for curve-fitting and for
function estimation in additive models. Moreover, there is a well-known
interpretation showing that these methods arise as Bayesian estimators from
intuitively appealing prior distributions. One can view the smoothing
problem as balancing fidelity to the data against smoothness through a
single
parameter. We show how the model can be extended to adapt to various
degrees of smoothness in the data. The model is equivalent to a spatially
adaptive prior. Two methods are presented for fitting the models, one
using generalized cross validation and a second fully Bayesian approach suitable
for Markov random field type priors. Applications are made to
nonparametric regression and density
estimation.
COFFEE: 3:45 p.m., 104 Snedecor
Hall
Seminar schedules and abstracts are
available via WWW:
http://www.stat.iastate.edu/
Jeanette La Grange
Department of Statistics
102
Snedecor
Iowa State University
Ames, IA 50010-1210
515 294-3440
(office)
515 294-4040 (fax)
http://www.stat.iastate.edu/directory/staff/jeanette.html