|
Activity Number:
|
248
|
|
Type:
|
Luncheons
|
|
Date/Time:
|
Tuesday, August 10, 2004 : 12:30 PM to 1:50 PM
|
|
Sponsor:
|
Section on Statistical Education
|
| Abstract - #300510 |
|
Title:
|
Using Simulations to Introduce Inference
|
|
Author(s):
|
Murray H. Siegel*+
|
|
Companies:
|
Sam Houston State University
|
|
Address:
|
Math. & Stats., Huntsville, TX, 77341,
|
|
Keywords:
|
simulation ; probability ; bias ; expectation ; chi-square
|
|
Abstract:
|
Students know the meaning of p value, but do they understand what it means? Simulations are used to help students develop an understanding. The first problem involves the hiring of 30 technicians; 40% of the qualified applicants are female. We expect 12 females to be hired but only eight are. Is there bias? Trials of a binomial simulation (30, .4) are run. The only reason for divergence from the expected is variation. What is the probability, based on the simulations, of hiring eight or fewer females? What does this say about the actual case? The second simulation involves a selection of a favorite cable network. The class votes and the results are recorded. Do the results confirm or refute that the four networks are equally favored? The chi-square statistic is introduced. A simulation is designed with four choices each with a probability of .25. The n is the same as the size of the class. Many simulations are run and for each the results are used to compute a chi-square statistic. What is the probability of obtaining a chi-square statistic greater than or equal to the one obtained for our vote? What does this say about the chance that the networks are equally favored?
|
- 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 |
