Research Methods

Homework: Chapters 5, 6 & 7

Due: Sunday, 3/28 by midnight

Overview: Please answer the following questions related to content we have covered in Chapters 5, 6 and 7. Feel free to use your textbook and the slides to help answer these questions, but please make sure to put everything in your own words. You can answer the parts of these questions in two sentences or less (you can even bullet!)

1. Here is a headline and story from the internet:

44 Percent of College Students Binge Drink

The National Institute on Alcohol Abuse and Alcoholism reports that the media may be portraying college life as it is: the percentage of college-age students who reported having engaged in binge drinking during the previous 30 days remained at 44 percent between 2002–2010, according to the annual National Survey on Drug Use and Health, sponsored by the Substance Abuse and Mental Health Services Administration. Some of the students that binge drink do so regularly. Half of the students who reported binge drinking engage in the behavior at least once per week. (Source: http://www.collegebingedrinking.net/44-percent-of-college-students-binge-drink.html)

a. What kind of claim is made in the headline (frequency, association, or causal)?

· Answer:

b. What is/are the variable(s) in the claim?

· Answer:

c. What seems to be the operationalization of the variable and is it a self-report, observational or physiological?

· Answer:

d. How might you establish the criterion validity of their “binge drinking” operationalization? What kind of data would you need to collect and how would you do that? (Hint: for this problem, use the known-groups paradigm for criterion validity. If you don’t remember what these are, read about them again in your textbook or check the slides).

· Answer:

2. Plan an observational study to see who is more likely to hold open a door for another person, men or women. Think about how to maximize your construct validity.

a. Will observers be biased about what they record? How might they influence the people they observe, if at all?

· Answer:

b. How will you evaluate the interrater reliability of your observers?

· Answer:

c. Write a two- to three-sentence operational definition of what it means to “hold the door” for somebody. Your operational definition should be clear enough that if you asked two friends to use it to code “holding the door” behavior, it would have good reliability and validity.

· Answer:

3. Locate a survey, poll or a rating system on a website (you can find them almost anywhere, but you might try www.gallup.com, www.pewresearch.org, www.buzzfeed.com, or www.usatoday.com). Then answer the following questions.

a. Evaluate the construct validity of the survey questions: Is the wording clear or might it be confusing? Are any questions double-barreled? Do any contain double negatives? Are the response options meaningful and clear?

· Answer:

b. Next, evaluate the external validity of this poll. Is the sample likely to be self-selected? If so, what do you think might be the characteristics of the people who self-select to take this poll? If you do not think it is self-selected, why not?

· Answer:

4. Imagine you’re planning to estimate the price of the average vehicles at a local dealership. The dealership has 10,000 cars, but you plan to sample only 200 of them. You will select a sample of 200 cars, record the price of each car, and use the average of the 200 cars to estimate the average price of the 10,000 vehicles in the bookstore. Assume that the dealership can give you access to a database that lists all 10,000 vehicles that it carries. Based on this information, answer the following questions:

a. What is the sample in this study, and what is the population of interest?

· Answer:

b. How might you collect a simple random sample of cars?

· Answer:

c. How might you collect a stratified random sample?

· Answer:

d. How might you collect a convenience sample?

· Answer:

e. How might you collect a systematic random sample?

· Answer:

f. How might you collect a cluster sample?

· Answer: