Functional Data Analysis on Circle

Objective

Match two functional data defined on a circle for cross comparison that reduces spatial variability in statistical analysis.

Data 

• subject1.data Coordinates and curvature measures of subject 1.
• subject2.data Coordinates and curvature measures of subject 2.

In MATLAB, perform

load subject1.data; load subject2.data

Data consists of 3 columns. First two columns are x and y coordinates of  a point on the corpus callosum boundary. The last column is the curvature estimated from a quintic spline.

8.0000 2.5000 -0.0764
7.3333 3.3333 -0.0745
6.5000 4.0000 -0.1196
5.0000 4.5000 -0.0929
4.5000 5.0000 -0.1081
3.0000 5.0000 -0.1938

Documentation

• Hoffmann, T.J. 2004. Subpixel morphometric analysis of corpus callosum with application to autism. BSc thesis. TR 1101. Department of Statistics, University of Wisconsin-Madison.
• Hoffmann, T.J., Chung, M.K., Dalton, K.M., Alexander, A.L., Wahba, G., Davidson, R.J. 2004. Subpixel curvature estimation of the corpus callosum via splines and its application to autism, 10th Annual Meeting of the Organization for Human Brain Mapping. Poster.

Last update 02/07/2005.