Download Introduction to Chance Models (Section 1.1) Introduction A key step

Survey
yes no Was this document useful for you?
   Thank you for your participation!

* Your assessment is very important for improving the work of artificial intelligence, which forms the content of this project

Document related concepts

Statistics wikipedia, lookup

History of statistics wikipedia, lookup

Transcript
Step 4: Draw Inferences.
12. Is the sample proportion who associated “Tim” with the face on the left greater than the
probability specified in the null hypothesis?
13. Is it possible that the sample proportion could turn out to be this large even if the null
hypothesis were true?
As we did with Buzz and Doris in Section 1.1, we will use simulation to investigate how
surprising the observed sample result would be, if in fact subjects were just as likely to
associate “Tim” with the face on the left as they were to associate “Bob” with the face on the left.
(Note also that our null model assumes the same probability for all subjects.)
14. We will now use the One Proportion applet to conduct this simulation analysis.
a. First enter the probability of success value specified in the null hypothesis.
b. Enter the appropriate sample size (number of subjects in this study).
c. Enter 1 for the number of samples, and press Draw Samples. Report the number of
“successes” in this simulated sample.
d. Now, select the radio button for “Proportion of successes.” Report the proportion of
successes in this simulated sample. Use your answer to “c” to verify how this value is
calculated.
e. Leaving the “Proportion of successes” radio button selected, click on Draw Samples
four more times. Do you get the same results each time?
f.
Now enter 995 for the number of samples and click on Draw Samples, bringing the
number of simulated samples to 1000. Comment on the center, variability, and shape
of the resulting distribution of sample proportions.
This distribution of simulated sample proportions is called the null distribution, because it is
based on assuming the null hypothesis to be true.
15. Restate the observed value of the sample proportion, p̂ , who associated “Tim” with the
face on the left.
June 27, 2014
MAA PREP workshop
21