RobertNiles.com
About Robert
Reporting Help
Finding Data on the Internet
Questions for Candidates
Stats Lessons
Mean
Median
Percent
Per capita
Standard Deviation
Margin of Error
Data Analysis
Sample Sizes
Stats Tests
Help Board
Bookstore


A Mathematician Reads the Newspaper

Read about reporters who blew it when trying to write about stats. A mathematician leads you through the tricks, citing contemporary examples.
More information
-->

Home > Statistics Every Writer Should Know > The Stats Board > Discusssion

Wilcoxon or t-test question
Message posted by Donna Blair-Richardson (via 204.108.241.14) on March 4, 2002 at 4:38 PM (ET)

I have two groups of students-one large (120) and one small (20) for which I matched on several variables such as SES, IQ, gender, teachers. When I finished matching, I only had nine students I could match on all these factors. I wanted to do a paired t-test, but thought I might need to do a Wilcoxon because I have a small sample and cannot be sure it follows a normal distribution. However, three of the nine matching scores are the same, so there is a difference of 0. Also, the scores are ranks themselves such as 0, 1, 2, 3, and 4. Should I even try to perform a statistical test? I'm not sure whether I have enough data to tell me anything worthwhile even if I were to conduct the test. Thank you for your help.



Your $5 contribution helps cover part the $500 annual cost of keeping this site online.

Niles Online Sites:RobertNiles.comTheme Park InsiderViolinist.com

RobertNiles.com™, the site, content and services 咀opyright 1996-2002, Robert Niles.
All rights reserved. Questions? Comments? Read my Privacy Policy, or E-mail me!