|
Activity Number:
|
442
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Thursday, August 12, 2004 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Statistical Education
|
| Abstract - #302150 |
|
Title:
|
Visualizing Confidence Intervals
|
|
Author(s):
|
Ronald L. Tracy*+
|
|
Companies:
|
Oakland University
|
|
Address:
|
Dept. of Economics, Rochester Hills, MI, 48309,
|
|
Keywords:
|
graphics ; computers ; teaching ; mean ; standard deviation ; variance
|
|
Abstract:
|
Students have difficulty understanding confidence intervals. They often mistakenly think that P(Xl< =mu< =Xu) = 0.95 means that there is a 0.95 probability that the parameter mu lies in the interval [Xl, Xu]. Although textbooks and instructors valiantly try to correct this interpretation, the notation does nothing to discourage it. The software Visualizing Confidence Intervals illustrates the correct interpretation of a confidence interval through simulation. The software allows the user to create confidence intervals for m using either the known standard deviation s or the estimated standard deviation s. It also enables students to create a confidence interval for the population variance s2. By changing the sample size the user can investigate its affect on a confidence interval. Although the default distribution of the X's is normal, the distribution can be changed to uniform or a variety of skewed distributions. This feature enables the user to investigate the effect the underlying distribution has on the interpretation of a confidence interval. Other features include a help system with search capability and "hot text."
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2004 program |
