Comparative Analysis of Clustering Techniques with an Application to K6-11 Mathematics Achievement Data

Authors:

Susan Deeb, Reina Galvez, Soeun Park, Nathan Robertson

Mentors:

  • Sam Behseta, Professor , california state university of Fullerton
  • David Pagni, Professor , california state university of Fullerton

In this research project, we consider three clustering techniques namely, hierarchical distance based clustering, model based clustering, and k-means in order to classify K6-11 students in Orange County, California based on their performances in California Exit Exam, GPA, California Standardized Tests, as well as, demographic parameters such as ethnicity and gender. Through an extensive simulation study we select a clustering method whose misspecification rate is lowest.


Presented by:

Soeun Park, Susan Deeb, Nathan Robertson

Date:

Saturday, November 23, 2013

Poster:

87

Room:

Poster Session 3 - Villalobos Hall

Presentation Type:

Poster Presentation

Discipline:

Mathematics