Nonparametric Tests for Ranked Data

Start: 03/11/2010 - 4:15pm
End  : 03/11/2010 - 5:15pm

Statistics/OR/Math Finance Seminar

Anna Bargagliotti, University of Memphis


Oftentimes nonparametric statistical methods are included as the last chapter
in a textbook. Typical statistics survey courses may either skip this chapter completely or
briefly cover the material at the end of the course. Because of this structure, students have
little exposure to nonparametric methods and may consider them as entirely separate from
the other statistics they have learned. Moreover, the nonparametric methods introduced
are typically very limited with much emphasis placed on step-by-step calculations and
little emphasis placed on intuition and motivation. However, many interesting research
problems and real-life situations require the knowledge of nonparametric statistics.
By characterizing the typically covered nonparametric methods using an overarching
unifying framework, we can provide students with intuition and the ability to make deep
connections to other mathematical content such as linear algebra, parametric statistics,
representation theory, and group theory. In this talk, I will introduce this framework
and illustrate some interesting problems that can be thought about and developed in a
statistics course.

Sprague Library Harvey Mudd College 3rd Floor Seminar Space

Misc. Information

Refreshments at 4pm