The sales director noticed that sales in the Midwest and Northeast regions were not as expected. Additional field training is necessary for the sales representatives in these regions.

After conducting a one-month training program, the sales director wants to determine the effectiveness of the training. After all, the company invested a significant amount of money in this program! So the sales director collects the sales data for the first month after the training. The sales director wants to compare the number of orders secured by those who attended the training program and those who didn’t attend. This study will help the company to determine the effectiveness of the training.

Part A
What type of study is the sales director conducting—a survey, an observational study, or an experiment? Justify your answer.

Part B
Describe how you would design the selection of subjects for this study. Assume there are 1,000 total sales representatives in the Midwest and Northeast regions, with 500 in each region. About half of the representatives in each region were assigned the training, and half were not. Be sure to also describe any processes you would include in your study to contribute to the best design possible.

Part C
Suppose the company decided to allow the sales representatives to choose whether to participate in the field-training program or to opt out. There are 400 who have chosen to participate in the field-training program and 600 who have opted out of the program. How might the self-selection process affect the statistical validity of the comparison of the change in the proportion of sales orders from new stores? Support your answer with a specific example.

Part D
Establishing causality is often a main focus of statistical studies. What is the best type of study to conduct to establish causality? Use the situation in this task to support your answer.