Robertas Gabrys

 

Department of Mathematics and Statistics

Utah State University

 

 

Detecting Change-Point in the Mean Function of Functional Observations

 

Functional data analysis (FDA) has been enjoying increased popularity over the last decade due to its applicability to problems which are difficult to cast into a framework of scalar or vector observations. Even if such standard approaches are available, the functional approach often leads to a more natural and parsimonious description of the data, and to more accurate inference and prediction results. Principal component analysis (PCA) has become a fundamental tool of functional data analysis. It represents the functional data as Xi(t) = µ(t) + Σ1≤ ℓ < ∞ ηi,υ(t), where µ(t) is the common mean, υ(t) are the eigenfunctions of the covariance operator, and the ηi,, are the scores. Inferential procedures assume that the mean function µ(t) is the same for all values of i.  If, in fact, the observations do not come from one population, but rather their mean changes at some point(s), the results of PCA are confounded by the change(s).  It is therefore important to develop a methodology to test the assumption of a common functional mean. We develop such a test using quantities which can be readily computed in the R package fda. The null distribution of the test statistic is asymptotically pivotal with a well-known asymptotic distribution. The asymptotic test has excellent finite sample performance. Its application is illustrated on temperature data from England.

 

Keywords: Change point detection, Functional data analysis, Mean of functional data, Significance test.

 

Joint work with:

István Berkes, Graz University of Technology, Graz, Austria

Lajos Horváth University of Utah, Salt Lake City, USA

Piotr Kokoszka, Utah State University, Logan, USA

 

Back to Colloquium Series