Degree Type

Dissertation

Date of Award

2015

Degree Name

Doctor of Philosophy

Department

Statistics

First Advisor

Petruţa Caragea

Second Advisor

Zhengyuan Zhu

Abstract

In many instances, it is useful to view data as a collection of curves, particularly when the questions motivating the analysis relate to properties of curves. In this case it makes sense to view the fundamental datum as a curve and refer to the collection of curves as functional data. This work deals with spatial models of functional data, where the underlying smooth curves are assumed to belong to a reproducing kernel Hilbert space. The methodology developed here is illustrated using satellite data of phenological measurements over India.

Copyright Owner

Daniel Clayton Fortin

Language

en

File Format

application/pdf

File Size

101 pages

Share

COinS