Question 4 (9 parts): Employees quit their jobs for many reasons, some of which are under employers' control. In manufacturing, "working conditions" is often cited as a reason by employees who quit. A major Texas manufacturer has two plantsone in Dallas and another in San Antonio. During the past year, the manufacturer asked employees who quit to rate the working conditions at their plant. The question and response scale are shown below: How would you rate working conditions at the plant? Very Poor Very Good 1 2 3 4 5 6 7

The responses from employees who recently quit the two plants are recorded below.

Working Conditions Ratings Question 4 Calculations Dallas Plant (Left column) San Antonio Plant (Right column) 3 4 6 4 3 4 5 3 4 5 3 5 4 3 4 4 4 4 3 4 5 5 4 5 3 4 6 4 2 3 1 3 4 4 5 4 3 4 6 4 4 5 4 5 3 3 4 4 4 6 4 4 3 6 3 4 4 5 4 4 3 5 1 4 2 4 3 2 3 1 4 3 2 4 4

Assume that [1] responses for the two plants are random samples, and [2] a mean rating below 4 means that employees who quit found working conditions to be "poor."

Conduct the appropriate hypothesis test to determine whether there is strong evidence for the alternative hypothesis that employees who quit the Dallas plant found working conditions to be "poor." Specifically, state the null hypothesis and compute the relevant test statistic. Is this a one-tailed test to the left, a one-tailed test to the right, or a two-tailed test?

b. What is the p-value for the test statistic in [a]? Write the Excel function you used to determine this p-value, including the inputs that you entered in the Excel function (do not give cell references; enter the numbers).

c. Based on the results from [a] and [b], what is your conclusion about the mean rating of working conditions at the Dallas plant at = .05?

d. Compute an 80% confidence interval for the mean rating of working conditions at the Dallas plant.

e. Compute descriptive statistics for beliefs about working conditions among employees who quit the Dallas and San Antonio plants. Specifically, compute sample means, variances, and sample sizes for responses at each plant.

f. Now, compare beliefs about working conditions among employees who quit between the two plants. Are the data paired or unpaired? Which is the most appropriate test of two means: for paired data, unpaired data with equal variances, or unpaired data with unequal variances? Hint: if necessary, refer to the descriptive statistics in part [e].

g. Conduct the appropriate hypothesis test to determine whether there is strong evidence that employees who quit believe that working conditions at the Dallas plant are worse on average than working conditions at the San Antonio plant. Specifically, state the null hypothesis and the alternative hypothesis, then compute the relevant test statistic.

h. Is the hypothesis test one- or two-tailed? What is the p-value for the test statistic in [g]?

i. Based on the results from [g] and [h], what is your conclusion at = 0.05 concerning beliefs about working conditions at the two plants among employees who quit