Constructions of fractal probability measures with uniform marginals
LE3 .A278 2015
2015
Mendivil, Franklin
Acadia University
Bachelor of Science
Honours
Mathematics and Statistics
Mathematics & Statistics
Bivariate probability measures can be decomposed into their marginal distributions and their \copula," a cumulative distribution function of a bivariate measure with uniform marginals which encodes the underlying dependence structure between the variables. In certain circumstances, these copulas can be fractal or self-similar in nature, and to model these we desire parameterized families of fractal measures with uniform marginals. We discuss a known construction for such a family and provide two new constructions. We also examine the dimension of the parameter space for each construction in order to assess their ability to approximate a given measure.
The author retains copyright in this thesis. Any substantial copying or any other actions that exceed fair dealing or other exceptions in the Copyright Act require the permission of the author.
https://scholar.acadiau.ca/islandora/object/theses:1194