Functional Data Analysis (FDA)

Most of the statistical methods include one or more observations taken from each of the individuals in a sample. As the area of interest gets broader, these observations take the form of curves or surfaces. Since there is a density on each point on a part of a plane or a line, these observed curves or surfaces are called functional data. It is assumed that this data which is observed on discrete points comes from an underlying real function. 

In most cases, observations are a function of time or a closely related variable. For example, temperature can be a function of time and length can be a function of age. As the capacity of tools and computers used for data collection and storage increase every day, statistical methods for analyzing functional data needs to be improved. Methods for analyzing functional data are referred to as "Functional Data Analysis (FDA)" by Ramsay and Dalzell (1991). 

An extensive list of references on FDA can be found here.

Matlab codes for Smoothed Functional Canonical Correlation Analysis can be downloaded from here. These codes are modified from Ramsay and should be used with that package.

Theoretical Background information for Functional Canonical Correlation Analysis can be downloaded from here.

 

 

 

Coefficient of Variation Function Graphs can be downloaded from here

.