# MA251: Statistics II

Unit 5: Nonparametric Statistics   Many methods in statistics assume that your population distribution is normal. However, there are many scenarios in which this is not true. In these cases, nonparametric statistics provide alternative statistical methods because they do not involve population parameters. Upon completion of this unit, you should be able to distinguish between parametric and nonparametric test procedures and perform basic nonparametric tests such as sign test and Wilcoxon signed-ranks test. You also will learn to identify situations for which nonparmetric tests are more appropriate.

This unit will take you approximately 20 hours to complete.

☐    Subunit 5.1: 4 hours

☐    Subunit 5.2: 16 hours

Unit5 Learning Outcomes
Upon successful completion of this unit, the student will be able to:

• explain the principles of nonparametric statistics; and
• perform nonparametric tests including sign test and Wilcoxon signed-ranks test.

5.1 Introduction to Nonparametric Tests   - Reading: Pennsylvania State University Center for Astrostatistics’s “Summer School in Statistics for Astronomers VI” Link: Pennsylvania State University Center for Astrostatistics’s “Summer School in Statistics for Astronomers VI” (PDF)

`````` Instructions: Browse to the schedule for June 10, 2010 and download
the PDF file for the lecture on “Nonparametric Statistics,” given by
Dr. Thomas Hettmansperger. Open the file and read the entire
lecture.

Studying this section should take approximately 4 hours.

displayed on the webpage above.
``````

5.2 Nonparametric Rank-Based Tests   - Lecture: Medical College of Wisconsin: John Klein’s “Uses and Abuses of Non-parametric Statistics in Medical Research” Link: Medical College of Wisconsin: John Klein’s “Uses and Abuses of Non-parametric Statistics in Medical Research” (PDF and YouTube)

`````` Instructions: Click on the lecture “Uses and Abuses of
Non-parametric Statistics” and watch the video. You may also want to
video, John Klein discusses the use of nonparametric tests including
sign test and Wilcoxon signed-ranks test. You will also learn when
to use nonparametric statistics. What is the most significant

Watching this lecture should take approximately 1 hour.

displayed on the webpage above.
``````

Instructions: Download the PDF file “nonpar.pdf” from the webpage (bullet #2 under “My own notes”) and read the whole chapter. In this reading you will learn about several nonparametric tests, including the sign test, the Wilcoxon signed-ranks test, the Mann-Whitney U test, and the Kruskal-Wallis H-test.

Reading this chapter should take approximately 4 hours.

• Assessment: Carnegie Mellon University: Judy Huixia Wang’s “Applied Nonparametric Statistics: Homework 5” The Saylor Foundation does not yet have materials for this portion of the course. If you are interested in contributing your content to fill this gap or aware of a resource that could be used here, please submit it here.

Submit Materials

• Assessment: McGraw Hill: Bowerman, O’Connell, Schermer, and Adcock’s “Business Statistics in Practice: Multiple Choice Quiz for Chapter 13” Link: McGraw Hill: Bowerman, O’Connell, Schermer, and Adcock’s “Business Statistics in Practice: Multiple Choice Quiz for Chapter 13” (HTML)

Instructions: Click on the link above and answer all questions in the quiz. Select your answers from choices given for each question. Click on “Submit Answers” at the bottom of the webpage when you have answered all the questions. The webpage will tell you whether your answer is correct and what the correct answer is.

Completing this quiz should take approximately 1 hour.