Principle Component Analysis
Conor J McCormick
Principle Component Analysis (PCA) is a powerful tool used in the field of statistics. In a given or collected sample of data, statisticians normally like to see correlations, or relationships, between variables in the sample. By examining the correlations between these variables, statisticians are able to create a linear representation to help make estimations for currently unknown values. Getting to this linear representation can be easy if there are only a few variables and/or the sample size is small. However, this is not always the case and this is where PCA comes into play. When the amount of variables taken is large it could lead to an even larger amount of correlation plots that must be looked at and could potentially be hard to interpret, but with PCA the number of plots can greatly be reduced and make it easier to see to correlation between variables. In my presentation, I plan to explain this technique.
Capstone Project - Undergraduate
Muhammad N Islam
Primary Advisor's Department
Stander Symposium poster
"Principle Component Analysis" (2017). Stander Symposium Posters. 1099.