Skip to main content

Nonparametric Statistical Methods (352-0-20)


Thomas A Severini
2006 Sheridan Road/Room 305/Department of Statistics

Meeting Info

Locy Hall 301: Mon, Wed 9:30AM - 10:50AM

Overview of class

The goal of this course is to provide an introduction to nonparametric function estimation. The topics to be covered include estimation of a distribution function, bootstrap methods, kernel density estimation, and nonparametric regression using kernel methods and smoothing splines (time permitting). The course will cover the basic theory underlying the methods, as well as applications of the methods to the analysis of data.

Registration Requirements

STAT 350 or a similar course on regression analysis; calculus at the level of Math 230.

Learning Objectives

1. To understand nonparametric methods used to estimate a distribution function.
2. To understand nonparametric methods used to estimate a density function.
3. To understand the nonparametric regression methods.
4 To be able to apply nonparametric methods to analyze data and draw the proper conclusions.
5. To be able to use statistical software to obtain nonparametric estimates.

Teaching Method


Evaluation Method

Grades will be based on homework, an exam, and a final project; these will be equally weighted.
There will be approximately five homework assignments.

Class Materials (Required)

Course notes will be available on Canvas; these notes will play the role of a course text.

Class Attributes

Formal Studies Distro Area