Low-Rank Models for Large Spatial Datasets

Matthias Katzfuss
Texas A & M University

With the proliferation of modern high-resolution measuring instruments mounted on satellites, planes, ground-based vehicles and monitoring stations, a need has arisen for statistical methods suitable for the analysis of large spatial datasets observed on large, heterogeneous spatial domains. Many statistical approaches to this problem rely on low-rank models, for which the process of interest is modeled as a linear combination of spatial basis functions plus a fine-scale-variation term. I describe how these low-rank models can be used for the analysis of global data, spatio-temporal data, and distributed data. For an extension of spatial low-rank models that includes a tapered (localized) fine-scale component, I discuss how to make inference on the number, locations, and shapes of the basis functions.

Wednesday, February 19
Mesa Lab VisLab
11:00 AM

About you
First name: 
Carolyn
Last name: 
Mueller
Phone extension: 
2491
Announcement contact
First name: 
Carolyn
Last name: 
Mueller
Phone extension: 
2491
Announcement duration
Start: 
Tuesday, February 18, 2014
End: 
Wednesday, February 19, 2014