I. MULTIPLE CHOICE -- Circle the one best answer for each.

1.    Which basic approach to social research produces the strongest inferences about causal relationships?
a. field and observational research
b. survey research
c. experimentation
***
d. available-data research

2.    Reliability assessment is a matter of checking for __________, while validity assessment is a matter of checking for __________.
a. consistency; accuracy
***
b. accuracy; consistency
c. similarity; dissimilarity
d. similarity; consistency

3.    In a study of the effects of religious beliefs on attitudes toward abortion, _________ would be the independent variable and _________ would be the dependent variable.
a. religious beliefs; attitudes toward abortion
***
b. attitudes toward abortion; religious beliefs
c. the control group; religious beliefs
d. the control group; attitudes toward abortion

4.      Induction is the process of
a. generating specific hypotheses from a general theory.
b. moving from data to theory. ***
c. both of the above.
d. none of the above.

5.      Several studies have found that students who drink heavily are more likely than other students to miss class, get behind in school work, and perform poorly on examinations.  From this finding, we can conclude confidently that
a. heavy drinking has a negative impact on academic performance.
b. heavy drinking impairs the cognitive tasks required to perform well academically.
c. poor academic performance causes distress which leads to heavy drinking.
d. there is an association between alcohol use and academic performance.
***

6.      To study whether women are stereotyped on television, Stephen Craig analyzed over 2,000 television commercials.  Among the information he coded for each commercial was the gender mix of the characters, the role of the primary visual character, and the type of product advertised.  Craig’s unit of analysis was
a. gender.
b. gender stereotypes.
c. women.
d. television commercials.
***
e. television.

7.    Suppose that among the 30 Major League baseball teams you found no association between a team’s average salary (or total player payroll) and team performance, as measured by won-loss record.  It would be an ecological fallacy to conclude from this finding that
a. teams with the lowest payrolls have the worst records.
b. attracting high-salaried players will not improve a team’s won-loss record.
c. there is no association between individual player salaries and player performance.
***
d. teams would be better off developing their farm systems than signing high-priced free|
    agents.
e. wealthy team owners drive up player salaries.

8.      To study marital adjustment among newlyweds, researchers selected a sample of couples from those who applied for marriage licenses in Santa Barbara County between April and June 1999.  They then interviewed the couples repeatedly over a four-year period.  This is an example of a
a. cross-sectional study.
b. trend study.
c. panel study.
***
d. cohort study.

9.    Suppose you hypothesize that the more sociology courses a student takes, the more sensitive he or she becomes to the needs of others.  So, you ask a random sample of UCSB students how many sociology courses they have taken and then have them complete a test of social sensitivity.  Finally, you calculate the association between the two variables.  This is an example of a
a. laboratory experiment.
b. social network survey
c. cross-sectional survey.
***
d. longitudinal survey.

10.  A positive association between variables X and Y in a bivariate table indicates that
a. X causes Y.
b. Y causes X.
c. both X and Y are caused by other factors.
d. either (a) or (b) could be correct.
e. any of the above could be correct. .
***

11.  Suppose for a given set of data that we regressed respondent’s years of education (Y) on father’s years of education (X) and obtained the following result:  Y = 9.39 + .34X.  The regression coefficient (+.34) is statistically significant. How much change in respondent’s education is associated with a change of 1 year in father’s education?
a. 1
b. 9.39 + .34
c. 9.39
d. .34
***

12.  Measures that are subject to very little random error but a major source of systematic error
a. are reliable but not valid.
***
b. are valid but not reliable
c. are neither reliable nor valid.
d. may be both reliable and valid.

13.  Coding categories for open-ended questions should be based upon
a. the researcher's data.
b. the researcher's theory.
c. both (a) and (b) ***
d. none of the above

14.  Suppose that a researcher conducting a survey of TV preferences, coded respondents’ favorite shows as comedy, drama, and news.  A major problem with this set of values is that:
a. they are ordinal-level categories.
b. they are not collectively exhaustive.
***
c. they are both exhaustive and mutually exclusive.
d. they use sample data.

15.  Which of the following is an example of nominal level measurement?
a. family size (number of children in a family).
b. political party affiliation (Republican, Democrat, Independent, Other, None).
***
c. educational attainment (years of schooling completed).
d. Income (dollars earned per year).

16.  Which of the following questions concerns reliability?
a. What does the Scholastic Aptitude Test (SAT) really measure?
b. Do attitude scales really tap personal feelings or just what people think
    investigators want to hear?
c. Is poverty best represented by measures of low absolute income (a minimum
    subsistence) or low relative income (e.g., 50% of national median income)?
d. How closely does self-reported church attendance correspond to actual
    church attendance?
e. Are scores on the even-numbered and odd-numbered items on this midterm
    highly correlated?
***

17.  A comprehensive exam purported to cover an entire quarter’s work only covers material from the first four weeks of the course. As a measure of how much students learned overall, this exam lacks
a. reliability
b. construct validity
c. content validity
***
d. criterion-related validity

18.  A researcher correlates scores on a test of "pilot ability" with whether or not students complete flight training. This is an example of assessing
a. test-retest reliability
b. test pilot reliability
c. criterion-related validity
***
d. construct validity

19.  In the National Health and Social Life Survey, which sought accurate statistics on sexual practices, “all people aged 18 to 59 with adequate English proficiency living in households located in the 50 states and District of Columbia” describes the
a. target population.
***
b. sampling frame.
c. sample.
d. sampling distribution.

20.  For which group would it be impossible to select a probability sample?
a. a sample of caterers in a city
b. a sample of visitors to Disney World
c. a sample of nursery school patients
d. a sample of cardiologists
e. none of the above
***

21.  A characteristic of a ____________ is called a ____________.
a. population;  statistic
b. sample;  parameter
c. population;  parameter***
d. statistic;  parameter

22.  Which of the following does not affect the size of the standard error?
a. the population variance
b. the population size ***
c. the sample size
d. the population standard deviation

23.   Which of the following sampling techniques depends for its effectiveness largely on the researcher’s knowledge and skill in selecting appropriate cases?
a. systematic sampling
b. simple random sampling
c. purposive sampling***
d. multistage cluster sampling

24.   Which of the following nonprobability sampling designs most closely resembles stratified random sampling?
a. convenience sampling
b. purposive sampling
c. quota sampling***
d. snowball sampling

25.   Drawing a sample of church members by first drawing a random sample of churches and then randomly sampling members from the selected churches is called a _________ sample.
a. whole
b. holy
c. cluster ***
d. stratified