1. Imagine you are designing a research experiment to test the effects of an anti-smoking campaign in a local high school (for 9^th and 10^th graders). First you will have a sample of students fill out surveys on their smoking behavior, some students will receive a special anti-smoking program, and then you will re-survey them after a few weeks. The school principal will not allow you to randomly assign students to treatment and control groups. How would you propose to use matching in this experiment?

2. In the example above, assume you were allowed to use random assignment to treatment and control groups. Explain the benefits of using random assignment. What assurances does it give you? What key validity problem does it guard against?

3. Explain the difference between internal and external validity for experiments.

4. In question number 1 above, if this experiment were carried out you would be experimenting with young human subjects. Assuming you obtain informed consent from the students who participate in the experiment, is it still a questionable ethical practice to conduct such experiments? Explain your answer.

 5. Whenever human subjects are used in research, there is a tradeoff between following ethical guidelines (protecting human subjects) and adhering to strict scientific methods. Do you think the protections offered to human subjects in the U.S. (as explained by Maxfield and Babbie) are adequate? Should we protect subjects more? Or do we not protect them enough? In your answer, explain how you think the balance should be struck.