2. From the news, record statements of politicians or other leaders about some social phenomenon. Which statements do you think are likely to be in error? What evidence could the speakers provide to demonstrate the validity of these statements?
1. What topic would you focus on if you could design a social research project without any concern for costs? What are your motives for studying this topic?
2. Develop four questions that you might investigate about the topic you just selected. Each question should reflect a different research goal: description, exploration, explanation, or evaluation OR cost-benefit, need analysis, political feasibility, or program evaluation. Be specific. Which question most interests you? Why?
1. Pick a social issue about which you think research is needed. Draft three research questions about this issue. Refine one of the questions and evaluate it in terms of the three criteria for good research questions.
2. Identify variables that are relevant to your three research questions. Now formulate three related hypotheses. Which are the independent and which are the dependent variables in these hypotheses?
1. Using recent newspapers or magazines, find three articles that report on large interview or survey research studies. Describe each study briefly. Then say (a) whether the study design was longitudinal or cross-sectional and (b) if that mattered—that is, if the study’s findings would possibly have been different using the alternative design.
1. Wearing your hat as a student of either ppol, hist, or socanth, Formulate four research questions about support for capital punishment. Provide one question for each research purpose: descriptive, exploratory, explanatory, and evaluative.
For class discussion (or too touchy?)
2. Concern with how research results are used is one of the hallmarks of ethical researchers, but deciding what form that concern should take is often difficult. You learned in this chapter about the controversy that occurred after Sherman and Berk (1984) encouraged police departments to adopt a pro-arrest policy in domestic abuse cases based on findings from their Minneapolis study. Do you agree with the researchers’ decision, in an effort to minimize domestic abuse, to suggest policy changes to police departments based on their study? Several replication studies failed to confirm the Minneapolis findings. Does this influence your evaluation of what the researchers should have done after the Minneapolis study was completed? What about Sherman’s (1992) argument that failure to publicize the Omaha study’s finding of the effectiveness of arrest warrants resulted in some cases of abuse that could have been prevented?
What does the code of ethics for your discipline include that the others don't and vice versa.
2. What questions would you ask to measure the level of trust among students? How about feelings of being “in” or “out” with regard to a group? Write five questions for an index, and suggest response choices for each. How would you validate this measure using a construct validation approach? Can you think of a criterion validation procedure for your measure?
1. Some people have said in discussions of international politics that “democratic governments don’t start wars.” How could you test this hypothesis? Clearly state how you would operationalize (1) democratic and (2) start.
5. Exercise your cleverness on this question: For each of the following, suggest two unobtrusive measures that might help you discover (a) how much of the required reading for this course students actually complete, (b) where are the popular spots to sit in a local park, and (c) which major U.S. cities have the highest local taxes.
1. When (if ever) is it reasonable to assume that a sample is not needed because “everyone is the same”—that is, the population is homogeneous? Does this apply to research such as Stanley Milgram’s on obedience to authority? What about investigations of student substance abuse? How about investigations of how people (or their bodies) react to alcohol? What about research on likelihood of voting (the focus of Chapter 8)?
3. What increases sampling error in probability-based sampling designs? Stratified rather than simple random sampling? Disproportionate (rather than proportionate) stratified random sampling? Stratified rather than cluster random sampling? Why do researchers select disproportionate (rather than proportionate) stratified samples? Why do they select cluster rather than simple random samples?
1. Locate one or more newspaper articles reporting the results of an opinion poll. What information does the article provide on the sample that was selected? What additional information do you need to determine whether the sample was a representative one?
3. Research on time use has been flourishing all over the world in recent years. Search the web for sites that include the words time use and see what you find. Choose one site and write a paragraph about what you learned from it.
THIS FOR LAB
1. Select a random sample using a table of random numbers (either one provided by your instructor or one from a website, such as www.bmra.com/extras/man-rand.htm). Compute a statistic based on your sample and compare it with the corresponding figure for the entire population. Here’s how to proceed:
- First, select a very small population for which you have a reasonably complete sampling frame. One possibility would be the listing of some characteristic of states in a U.S. Census Bureau publication, such as average income or population size. Another possible population would be the list of asking prices for houses advertised in your local paper.
- Next, create a sampling frame, a numbered list of all the available elements in the population. If you are using a complete listing of all elements, as from a U.S. Census Bureau publication, the sampling frame is the same as the list. Just number the elements (states). If your population is composed of housing ads in the local paper, your sampling frame will be those ads that contain a housing price. Identify these ads, and then number them sequentially, starting with 1.
- Decide on a method of picking numbers out of the random number table, such as taking every number in each row, row by row, or moving down or diagonally across the columns. Use only the first (or last) digit in each number if you need to select 1 to 9 cases or only the first (or last) two digits if you want 10 to 99 cases.
- Pick a starting location in the random number table. It’s important to pick a starting point in an unbiased way, perhaps by closing your eyes and then pointing to some part of the page.
Record the numbers you encounter as you move from the starting location in the direction you decided on in advance, until you have recorded as many random numbers as the number of cases you need in the sample. If you are selecting states, 10 might be a good number. Ignore numbers that are too large (or small) for the range of numbers used to identify the elements in the population. Discard duplicate numbers.
- Calculate the average value in your sample for some variable that was measured (for example, population size in a sample of states or housing price for the housing ads). Calculate the average by adding the values of all the elements in the sample and dividing by the number of elements in the sample.
- Go back to the sampling frame and calculate this same average for all the elements in the list. How close is the sample average to the population average?
- Estimate the range of sample averages that would be likely to include 90% of the possible samples.
2. Federal regulations require special safeguards for research on persons with impaired cognitive capacity. Special safeguards are also required for research on prisoners and on children. Do you think special safeguards are necessary? Why or why not? Do you think it is possible for individuals in any of these groups to give “voluntary consent” to research participation? What procedures might help make consent to research truly voluntary in these situations? How could these procedures influence sampling plans and results?
2. Researchers often try to figure out how people have changed over time by conducting a cross-sectional survey of people of different ages. The idea is that if people who are in their 60s tend to be happier than people who are in their 20s, it is because people tend to “become happier” as they age. But maybe people who are in their 60s now were just as happy when they were in their 20s and people in their 20s now will be just as unhappy when they are in their 60s. (That’s called a cohort effect.) We can’t be sure unless we conduct a panel study (survey the same people at different ages). What, in your experience, are the major differences between the generations today in social attitudes and behaviors? Which would you attribute to changes as people age and which to differences between cohorts in what they have experienced (such as common orientations among baby boomers)? Explain your reasoning.
1. From newspapers or magazines, find two recent studies of education (reading, testing, etc.). For each study, list in order what you see as the most likely sources of internal invalidity (selection, mortality, etc.).
3.Volunteer for an experiment. Contact the psychology department at your school and ask about opportunities for participating in laboratory experiments. Discuss the experience with your classmates.
Ethics (for class debate?)
2. In their study of “neighborhood effects” on crime, sociologists Robert Sampson and Stephen Raudenbush (1999) had observers drive down neighborhood streets in Chicago and record the level of disorder they observed. What should have been the observers’ response if they observed a crime in progress? What if they just suspected that a crime was going to occur? What if the crime was a drug dealer interacting with a driver at the curb? What if it was a prostitute soliciting a customer? What, if any, ethical obligation does a researcher studying a neighborhood have to residents in that neighborhood? Should research results be shared at a neighborhood forum?
Talking (Maybe do this as an exercise or lab?)
2. In-person interviews have for many years been the “gold standard” in survey research because the presence of an interviewer increases the response rate, allows better rapport with the interviewee, facilitates clarification of questions and instructions, and provides feedback about the interviewee’s situation. However, researchers who design in-person interviewing projects are now increasingly using technology to ensure consistent questioning of respondents and to provide greater privacy while respondents are answering questions. But having a respondent answer questions on a laptop while the interviewer waits is a very different social process than asking the questions verbally. Which approach would you favor in survey research? What trade-offs can you suggest there might be in quality of information collected, rapport building, and interviewee satisfaction?
2. Each of the following questions was used in a survey that we received at some time in the past. Evaluate each question and its response choices using the guidelines for question writing presented in this chapter. What errors do you find? Try to rewrite each question to avoid such errors and improve question wording.
Multiple examples in text
1. Write 10 questions for a 1-page questionnaire that concerns a possible research question. Your questions should operationalize at least three of the variables on which you have focused, including at least one independent and one dependent variable. (You may have multiple questions to measure some variables.) Make all but one of your questions closed ended.
2. Conduct a preliminary pretest of the questionnaire by conducting cognitive interviews with two students or other persons like those to whom the survey is directed. Follow up the closed-ended questions with open-ended probes that ask the respondents what they meant by each response or what came to mind when they were asked each question. Take account of the feedback you receive when you revise your questions.
3. Polish the organization and layout of the questionnaire, following the guidelines in this chapter. Prepare a rationale for the order of questions in your questionnaire. Write a cover letter directed to the appropriate population that contains appropriate statements about research ethics (human subject issues).
1. Become a media critic. For the next week, scan a newspaper or some magazines for statistics. How many articles can you find that use frequency distributions, graphs, and the summary statistics introduced in this chapter? Are these statistics used appropriately and interpreted correctly? Would any other statistics have been preferable or useful in addition to those presented?
1. (LAB?) Create frequency distributions from lists in U.S. Census Bureau reports on the characteristics of states, cities, or counties or any similar listing of data for at least 100 cases (http://factfinder2.census.gov/faces/nav/jsf/pages/index.xhtml). You will have to decide on a grouping scheme for the distribution of variables, such as average age and population size; how to deal with outliers in the frequency distribution; and how to categorize qualitative variables, such as the predominant occupation. Decide what summary statistics to use for each variable. How well were the features of each distribution represented by the summary statistics? Describe the shape of each distribution. Propose a hypothesis involving two of these variables, and develop a crosstab to evaluate the support for this hypothesis. Describe each relationship in terms of the four aspects of an association after converting cell frequencies to percentages in each table within the categories of the independent variable. Does the hypothesis appear to have been supported?
1. (For charts workshop) Review the frequency distributions and graphs in this chapter. Change one of these data displays so that you are “lying with statistics.” (You might consider using the graphic technique discussed by Orcutt & Turner 1993.)
1. Maurice Punch (1994) once opined that “the crux of the matter is that some deception, passive or active, enables you to get at data not obtainable by other means” (p. 91). What aspects of the social world would be difficult for participant observers to study without being covert? Might any situations require the use of covert observation to gain access? What might you do as a participant observer to lessen access problems while still acknowledging your role as a researcher?
2. Review the experiments and surveys described in previous chapters. Pick one and propose a field research design that would focus on the same research question but use participant observation techniques in a local setting. Propose the role that you would play in the setting, along the participant observation continuum, and explain why you would favor this role. Describe the stages of your field research study, including your plans for entering the field, developing and maintaining relationships, sampling, and recording and analyzing data. Then discuss what you would expect your study to add to the findings resulting from the study described in the book.
1. Conduct a brief observational study in a public location on campus where students congregate. A cafeteria, a building lobby, or a lounge would be ideal. You can sit and observe, taking occasional notes unobtrusively and without violating any expectations of privacy. Observe for 30 minutes. Write up field notes, being sure to include a description of the setting and a commentary on your own behavior and your reactions to what you observed.
3. Develop an interview guide that focuses on a research question addressed in one of the studies in this book. Using this guide, conduct an intensive interview with one person who is involved with the topic in some way. Take only brief notes during the interview; then write up as complete a record of the interview as you can immediately afterward. Turn in an evaluation of your performance as an interviewer and note taker together with your notes.
1. Should covert observation ever be allowed in social science research? Do you believe that social scientists should simply avoid conducting research on groups or individuals who refuse to admit researchers into their lives? Some have argued that members of privileged groups do not need to be protected from covert research by social scientists—that this restriction should only apply to disadvantaged groups and individuals. Do you agree? Why or why not?
2. Should any requirements be imposed on researchers who seek to study other cultures to ensure that procedures are appropriate and interpretations are culturally sensitive? What practices would you suggest for cross-cultural researchers to ensure that ethical guidelines are followed? (Consider the wording of consent forms and the procedures for gaining voluntary cooperation.)
2. Does qualitative data analysis result in trustworthy results—in findings that achieve the goal of “authenticity”? Why would anyone question its use? What would you reply to the doubters?
Narrative analysis provides the “large picture” of how a life or event has unfolded, whereas conversation analysis focuses on the details of verbal interchange. When is each method most appropriate? How could one method add to the other?
4. Ethnography and grounded theory both refer to aspects of data analysis that are an inherent part of the qualitative approach. What do these approaches have in common? How do they differ? Can you identify elements of these two approaches in this chapter’s examples of ethnomethodology, conversation analysis, and narrative analysis?
2. Write a narrative in class about your first date, car, college course, or something else you and your classmates agree on. Then collect all the narratives, and analyze them in a “committee of the whole.” Follow the general procedures discussed in the example of narrative analysis in this chapter.
1. Pictures are worth a thousand words, so to speak, but is that a thousand words too many? Should qualitative researchers (like yourself) feel free to take pictures of social interaction or other behaviors anytime, anywhere? What limits should an institutional review board place on researchers’ ability to take pictures of others? What if the “after” picture of the Apache children in this chapter (Exhibit 10.7) also included Captain Pratt in a military uniform?
4. Susan Olzak, Suzanne Shanahan, and Elizabeth McEneaney (1996) developed a nomothetic causal explanation of variation in racial rioting in the United States over time, whereas Griffin’s (1993) explanation of a lynching can be termed idiographic. Discuss the similarities and differences between these types of causal explanation. Use these two studies to illustrate the strengths and weaknesses of each.
1. Paul Ekman, the psychologist cited who studies evidence of emotions in people’s faces, has written extensively on this topic, and his work is widely used by police departments and even intelligence agencies. Find and read his findings on how to spot if someone is lying.
Doing1. If you’ve read some of Ekman’s work as suggested in “Finding Research,” use his methods to watch people at some event—a sporting competition, maybe, or a reception. Keep track in detail of what they look like, and see if you can spot unexpected or socially awkward reactions. What might they mean?
3. (Set up conversation between the three groups?) Select a major historical event or process, such as the Great Depression, World War II, the civil rights movement, or the war in Iraq. Why do you think this event happened? Now, select an historical or comparative method that you think could be used to test your explanation. Why did you choose this method? What type of evidence would support your proposed explanation? What problems might you face in using this method to test your explanation?
6.Exhibit 11.12 identifies voting procedures and the level of turnout in 1 election for 10 countries. Do voting procedures appear to influence turnout in these countries?