Midterm Exam Statistics 537 Fall, 2011

The Instructions: This is an open book, open notes exam. Since this is an examination, all work is to be done individually. Outside consultation is not permitted. Your solutions to these problems should be presented in a clear and concise fashion, presented in a MS Word document. Include selected computer output in your write-up, as needed.

The Exam: 1. A pharmaceutical company manufactures 25-mg antihistamine tablets. A random sample of 30 tablets is obtained from a recent batch, and the potencies of these tablets is given in the file Potencies.txt. a. Create a stem-and-leaf plot for these data. b. Assess the normality of these data. c. Provide a 99% Confidence Interval for the average potency. d. Based on your results for part (c), can we conclude that the average potency is 25 mg as advertised?

2.

The file WLabor.xls contains data on the percentage of women in the workforce in 1968 and in 1972. a. Compute the difference scores between percentages for each year and create a stem-and-leaf plot for these difference scores. b. Assess the normality of these difference scores. c. Based upon these results, use either the Wilcoxon Signed Ranks test or the t-test to determine whether there is a difference between the average percentages in 1968 and the average percentages in 1972. Use =0.05. d. If you decide that the mean percentages differ, estimate this difference with a 95% Confidence Interval.

3.

The data contained in the file Weight.txt describes the length of time that overweight males remained on one of two therapies, A or B, involving different weight reducing agents.. a. Create a stacked histogram of the data from each of the two therapies, as well as side-by-side box-and-whisker plots. b. Assess the normality of the data from each of the two therapies. c. Provide a 95% Confidence Interval for the mean times for each of the two therapies. d. Determine if the variances of the times from the two therapies are equal. e. Test whether the means of the times of the two therapies are equal, using either the t-test or the Wilcoxon Rank Sum test, based on the information you obtained above. f. If you decide that the means of these two therapies are not equal, estimate this difference with a 95% Confidence Interval.

4.

In a study published in 1989, researchers investigated salaried and wageearning employees with respect to medical clearance to return to work following illness. Personnel data were used to identify 216 illness absences requiring medical clearance. Then medical records were reviewed to determine whether clearance for return to work had been granted. These data are given in the following table:

Employee Type Salaried Wage-earning

Clearance granted 49 117

Clearance not granted 33 17

a. b. c. d.

Using =0.01, Determine whether clearance to return to work in independent of employee type. Estimate the proportion of salaried workers granted clearance. Estimate the proportion of wage-earning workers granted clearance. Estimate the difference in these two proportions.