The project was a data-mining project aiming at discovering hidden relationships or meanings from huge volumes of data. More specifically, Constance Williams has worked on the analysis of the children health data, which is a research dataset about various health and environmental factors over 137,000 patients, to find the most influential environmental factors to affect child obesity.
For this purpose, the student needed to learn and apply various statistical methods, such as linear regressions and Canonical Correlation Analysis, by using R, one of the most popular research tools for statistical analysis. During the internship period, the student had a chance to learn cutting-edge technologies and tools used in industry and academia. |