Using techniques from an earlier section, we can find a confidence interval for _d. Consider a random sample of n matched data pairs A, B. Let d = BA be a random variable representing the difference between the values in a matched data pair. Compute the sample mean of the differences and the sample standard deviation s_d. If d has a normal distribution or is mound-shaped, or if n 30, then a confidence interval for _d is as follows...... c = confidence level (0 < c < 1), d E < _d < d + E, whereE=tc sd/ square root of n

B: Percent increase for company	14	6	20	18	6	4	21	37
A: Percent increase for CEO	26	29	14	14	4	19	15	30

(a) Using the data above, find a 95% confidence interval for the mean difference between percentage increase in company revenue and percentage increase in CEO salary. (Round your answers to two decimal places.)

lower limit upper limit

(b) Use the confidence interval method of hypothesis testing to test the hypothesis that population mean percentage increase in company revenue is different from that of CEO salary. Use a 5% level of significance. 1. Since _d = 0 from the null hypothesis is not in the 95% confidence interval, reject H₀ at the 5% level of significance. The data indicate a difference in population mean percentage increases between company revenue and CEO salaries. 2. Since _d = 0 from the null hypothesis is in the 95% confidence interval, reject H₀ at the 5% level of significance. The data do not indicate a difference in population mean percentage increases between company revenue and CEO salaries. 3. Since u_d= 0 from the null hypothesis is not in the 95% confidence interval, do not reject H₀ at the 5% level of significance. The data indicate a difference in population mean percentage increases between company revenue and CEO salaries. 4. Since _d = 0 from the null hypothesis is in the 95% confidence interval, do not reject H₀ at the 5% level of significance. The data do not indicate a difference in population mean percentage increases between company revenue and CEO salaries.