Department of Statistics
University of Georgia
Bivariate Penalized Splines for Regression
In this work we are interested in smoothing data over complex irregular boundaries or interior holes. We propose bivariate penalized spline estimators over triangulations using energy functional as the penalty. We establish the consistency and asymptotic normality for the proposed estimators, and study the convergence rates of the estimators. A comparison with thin-plate splines is provided to illustrate some advantages of this spline smoothing approach. The proposed method can be easily applied to various smoothing problems over arbitrary domains, including irregularly shaped domains with irregularly scattered data points.
Sponsored by the Department of Mathematical Sciences
Host: Qiongxia Song
Refreshments will be served in Room TBD 30 minutes before the talk begins.