LE3 .A278 2006

2006

Cabilio, Paul
Zhang, Ying

Acadia University

Master of Science

Masters

Mathematics and Statistics

Mathematics & Statistics

This thesis evaluates and compares three metrics of medication compliance: CMA, mSSAI and SSAI. The CMA metric is used in current research, while mSSAI and SSAI are newly proposed metrics. Di®erent aspects of each metric are discussed. Next, these three metrics are used to calculate compliance levels from clinical trial study data on patients with Heart Failure (HF) illness. The HF patients in the study took medications from four di®erent drug classes during the course of their treatment. Both parametric and nonparametric approaches are made use of in order to explore the distributional properties of the CMA, mSSAI and SSAI metrics. A nonparametric approach utilizes kernel density estimation as a preliminary explo- ration for comparison of the drug classes' density curves. In addition, a parametric approach, the Pearson system of distributions, is used to e®ectively identify a para- metric family for each HF drug class for all three metrics. As a result, the beta and Laplace family of distributions are identi¯ed in this process.

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:119