In: Statistics and Probability
Activity 4: Confidence interval for a difference in proportions We will use StatKey to calculate a confidence Interval for a difference in proportions using the StatKey dataset “Use Text Messages (by age)”, which compares text messaging use between teens and adults.
1. Create a bootstrap distribution of 4000 bootstrap differences of proportions using this sample. Use the "Two-tail" option to find the boundaries giving 95% in the middle of the bootstrap distribution.
2. What is the difference in sample proportions for this sample?
3. What is the standard error of this difference?
4. Switch to StatKey's Normal distribution and edit the parameters so the mean is the sample statistic from question 2 and the standard error is the answer from question Again, use the "Two-tail" option to find the boundaries giving 95% in the middle of this normal distribution.
5. Compare the answer from the normal distribution to what you found from the bootstrap distribution. Are the results similar?
http://www.lock5stat.com/StatKey/bootstrap_2_cat/bootstrap_2_cat.html
1. The bootstrap distribution of 4000 bootstrap differences of proportions samples are given as follow.
2. The difference in sample proportions for this sample is 0.160.
3. The standard error of this difference is 0.015.
4. StatKey's Normal distribution with the same mean and the same standard deviation
6. The results are similar from normal distribution and what i found from the bootstrap distribution.