Scientific Program > Topic 3 >
Session 3G. Nonparametric Methods

Session Organizer(s)

Noel Veraverbeke (Belgium) noel.veraverbeke@luc.ac.be

Session Abstract

The well known parametric statistical methods such as the two-sample t-test, the analysis of variance, the simple linear regression analysis, require the assumption that the data come from a normal distribution. Checking this model assumption can be problematic, especially in small samples.

The so-called nonparametric methods began some fifty years ago. Initially they aimed at distribution-free procedures, not requiring the restriction of a parametric model for the data. These methods are typically based on the ranks of the observations and turn out to be less computational and conceptually simpler than their parametric counterparts. In later years further important classes of nonparametric methods developed. There is the important class based on the empirical distribution function. Efron' s bootstrap is clearly a modern technique of this type. A further area, in full development, is the methodology for estimation of smooth functions. For example, the kernel methods for estimating density functions, distribution functions, are very useful in practical data analysis. Related is also the broad field of nonparametric regression function estimation. It is also important to note that the ever more powerful computer packages greatly influenced the whole area of nonparametric statistics.

It is the intention that the speakers will cover several interesting topics in the field of nonparametrics. Advantages and disadvantages will be discussed and attention will be given to the way the methods fit in the teaching of our statistics courses. The examples can come from all fields of application, including medicine, engineering, econometrics, social sciences, etc.

Presentations

Presentation 3G1 The Teaching and Practical Implementation of the Non-parametric Bootstrap Cornelia J. Swanepoel (South africa)
Presentation 3G2 A Sort Introduction to Nonparametric Curve Estimation Ricardo Cao (Spain)
Presentation 3G3 Visual Basic Applications and Spreadsheet for Teaching Estimation of Nonparametric Density and Regression Functions Federico Palacios-Gonzalez (Spain)
Presentation 3G4 Tests for Interaction in a Two-way Layout: Should They Be Included in a Nonparametrics Course? Thomas Hettmansperger (USA)

Back to top

ICOTS-6, The Sixth International Conference on Teaching Statistics - International Program Committee (IPC) Website.
Copyright © 2001 by the IASE. All rights reserved. This information is subject to change without notice. This page was last modified on July 2, 2002.
For questions or comments, contact the Webmaster, Dagan Ben-Zvi.