Suppose that the human resources department at a large company desires to know if occupational stress varies with age. They classify employees into four age classes:
A: below age 30, B: age 30-39, C: age 40-55, D over age 55
These four groups are the levels of factor age – there are four levels here. With this design, we shall have multiple observations in the form of scores on an Occupational Stress Assessment test from a number of employees belonging to the four levels of factor age. We are interested to know whether all the levels i.e. age groups have equal stress on the average.
The sample data appear in the R data frame occupstress.Rdata.
1. Build side-by-side boxplots as a visual comparison of the test scores by age classification. Interpret them. You won’t be able to upload them; therefore, you will have to describe them to me in a word picture.
2. Run a traditional one-way analysis of variance to see if there is a significant difference in mean stress level between at least two of the age classes. Show all elements of the test.
3. If so, determine where differences lie using Bonferroni & Tukey multiple comparisons. Do you get different results? (Don’t just answer yes or no. Explain any differences.)