Name: 
 

Methods Midterm Two Study Guide - Fall 2003



True/False
Indicate whether the sentence or statement is true or false.
 

1. 

The study of deviant cases is an example of a purposive study.
 

2. 

A confidence interval at the 68 percent confidence level will be larger than one constructed at the 95 percent confidence level.
 

3. 

In a natural experiment, the researcher does NOT manipulate the independent variable.
 

4. 

Campbell and Stanley suggest that, given proper randomization in the assignment of subjects to experimental and control groups, there is no need for pretesting.
 

5. 

To overcome the effect of the order of questions on respondent's answers, it is important to randomize the order of the items.
 

6. 

A demonstrated lack of response bias is more important that a high response rate.
 

7. 

Evaluation research as a scientific undertaking is a matter of finding out whether something happened or didn't happen.
 

8. 

The most effective evaluation research combines quantitative and qualitative components.
 

9. 

An antecedent control variable is one that occurs between the independent and the dependent variable in time.
 

10. 

Ex post facto hypothesizing refers to the development of hypotheses "predicting" relationships that have already been observed in the data.
 

11. 

The number of cases omitted from a bivariate analysis because of missing data should be included in the table.
 

12. 

Whereas univariate analysis and subgroup comparisons focus on the descriptions of the people under study, the focus of bivariate analysis is on the relationships among the variables themselves.
 

13. 

A bivariate table is read by comparing the independent variable subgroups with one another in terms of a given attribute of the dependent variable.
 

Multiple Choice
Identify the letter of the choice that best completes the statement or answers the question.
 

14. 

In general, as sample size increases,
a.
the standard error increases in size
b.
the standard error decreases in size
c.
the standard error will remain the same regardless of changes in sample size
d.
the standard error is a constant
e.
the standard error fluctuates in size
 

15. 

The chief purpose of probability sampling is to be able to select
a.
simple random samples
b.
a sample whose statistics will accurately portray an unknown population parameter
c.
a sample whose parameters will accurately portray an unknown population statistic
d.
a sample whose statistics will accurately portray a known population parameter
e.
a sample whose unknown statistics will accurately portray a known parameter
 
 
_______________________________________________________________________

Research on Hospital Personnel

You are doing research on hospital personnel-orderlies, technicians, nurses, and doctors. You want to be sure you draw a sample that has cases in each of the personnel categories.

_______________________________________________________________________
 

16. 

Refer to Research on Hospital Personnel. You want to use probability sampling. An appropriate strategy would be
a.
simple random sampling
b.
quota sampling
c.
cluster sampling
d.
stratified sampling
e.
accidental sampling
 

17. 

A disadvantage of stratified sampling is that it
a.
denies you the use of probability theory
b.
requires you to have some prior knowledge about the elements in the population prior to drawing the sample
c.
usually increases the standard error
d.
usually requires samples that are larger in size than those required by simple random sampling
e.
none of the above
 

18. 

A study population is
a.
the hypothetical aggregation of all the elements in a study
b.
the theoretically specified aggregation of study elements
c.
that aggregation of elements from which the sample is actually selected
d.
that aggregation or set of elements considered for selection in some stage of sampling
e.
that aggregation of elements from which information is collected
 

19. 

In order to ensure that experimental and control groups are similar before the experiment begins, social scientists sometimes
a.
pair subjects who are identical on relevant variables and assign one to the control group and one to the experimental group
b.
create groups that are equivalent in terms of their averages on some relevant variables
c.
assign subjects randomly to the experimental and control groups
d.
match subjects on relevant variables
e.
all of the above
 

20. 

Which of the following is LEAST suited to providing clear evidence about a causal relationship between the independent and dependent variables?
a.
classical experimental design
b.
Solomon four-group design
c.
posttest-only control group design
d.
one-shot case study
e.
all of the above are equally effective in providing evidence of a causal relationship
 

21. 

The double-blind experiment is one in which
a.
the experimenters do not know which is the experimental group and which is the control group
b.
the experimental subjects do not know that they are in the experimental group, and the control group subjects know that they are in the control group
c.
neither the subjects in the experimental or control groups nor the experimenters know which are the experimental and control groups
d.
the control group subjects do not know that they are in the control group, and the experimental group subjects know that they are in the experimental group
e.
the experimental and control groups are given placebos
 

22. 

Experiments are least appropriate for research projects that involve
a.
small-group interaction
b.
hypothesis testing
c.
testing relatively limited and well-defined concepts and propositions
d.
descriptive purposes
e.
explanatory purposes
 

23. 

Without randomly assigning subjects, a researcher administers the experimental stimulus to the experimental group and then measures the dependent variable in both the experimental and comparison groups. This design is known as the
a.
one-group pretest-posttest design
b.
one-shot case study
c.
static-group design
d.
classical experimental design
e.
posttest-only control group design
 

24. 

In general, survey research is an appropriate observational method for
a.
describing a population too large to observe directly
b.
descriptive, exploratory, and explanatory purposes
c.
the measurement of attitudes prevalent in a larger population
d.
studies that have individual people as the unit of analysis
e.
all of the above
 

25. 

Professor Smidlapp mailed a questionnaire to students on the issue of academic dishonesty. Smidlapp planned to use inferential statistics in the analyses and was concerned about the response rate. You tell Smidlapp that technically the use of inferential statistics assumes that
a.
all members of the population complete and return the questionnaire
b.
all members of the initial sample complete and return the questionnaire
c.
at least 50 percent of the members of the initial sample complete and return the questionnaire
d.
at least 50 percent of the population complete and return the questionnaire
e.
the overall response rate exceeds 75 percent
 

26. 

One of the most important natural abilities that interviewers must have is the ability to
a.
dress in a fashion that is similar to the people being interviewed
b.
determine very quickly the kind of person the respondent will feel most comfortable with
c.
rephrase questions in their own words
d.
probe for responses
e.
pry into the respondent's personal life
 

27. 

Interview surveys have a number of advantages over mail surveys; which of the following is NOT one of those advantages?
a.
Higher response rates.
b.
There is generally a smaller number of "don't knows" and "no answers".
c.
There is a smaller number of relevant responses given.
d.
Observations can be made.
e.
All of the above are advantages of the interview.
 

28. 

In contrast to interviews, self-administered questionnaires have the advantage(s) of
a.
being more effective in dealing with complicated issues
b.
producing fewer incomplete questions
c.
dealing with the context of social life
d.
handling sensitive issues more effectively if the surveys are anonymous
e.
all of the above
 

29. 

Which of the following statements is (are) INCORRECT?
a.
Closed-ended questions should limit respondents to three or four choices.
b.
Closed-ended questions should have response categories that are mutually exclusive and exhaustive.
c.
Closed-ended questions should provide uniformity of response.
d.
Closed-ended questions should cover the range of likely responses.
e.
Closed-ended questions are appropriate when relevant answers to questions are relatively clear.
 

30. 

The questionnaire item "Did you file federal and state income tax reports last year?" with a response set of yes, no, can't remember, other, is an example of a(n)
a.
open-ended question
b.
ordinal question
c.
double-barreled question
d.
negative item
e.
ratio variable
 

31. 

After the delivery of their baby, new parents in hospital A were given a poison control test. While at the hospital, they attended a training session on poison control. At the end of a week, they were given the poison control test again. After the delivery of their baby, new parents in hospital B were given the poison control test. One week later, they were given the test again. What kind of design is being used?
a.
pretest-posttest control group
b.
time-series
c.
nonequivalent control group
d.
cross-sectional design
e.
multiple time-series
 

32. 

Which of the following would NOT be appropriate for measurement in evaluation research?
a.
dependent variable(s)
b.
the experimental context
c.
the outcome(s) of the experiment
d.
the independent variable(s)
e.
all of the above should be measured
 

33. 

Social indicators research combines
a.
evaluation research with interviewing
b.
evaluation research with the analysis of existing data
c.
the analysis of existing data with questionnaires
d.
the analysis of existing data with the historical/comparative approach
e.
evaluation research with the historical/comparative approach
 
 
_______________________________________________________________________

IQ Scores
 
You examined the IQ scores of children at several high schools. You finally select two high schools where the children appear similar in terms of IQ scores, family income, family religion, and the like. You then matched two classes from each grade (9 to 12) from each high school. In one high school, you plan to offer a course on study skills in the selected classes, and in the other high school, you plan to have students follow their "normal" curriculum. After obtaining permission from the principals, parents, and children to do your research, you arrive at the first school to begin the study skills class. You find that the classes you had selected are on field trips and that the principal has assigned another class of the same grade level to you.

_______________________________________________________________________
 

34. 

Refer to IQ Scores. This illustrates the problem(s) of
a.
logistics
b.
administrative control
c.
ethics
d.
all of the above
e.
only a and b are correct
 

35. 

In a study that examined whether the use of mediation in divorces results in "fairer" settlements, the "outcome" is the
a.
use of mediation
b.
"fairer" settlement
c.
actual divorce
d.
judge's decision
e.
cannot tell from the given information
 

36. 

If gun control legislation were passed to reduce the number of homicides, which of the following graphs would be most likely to convince you that the legislation was producing the intended effect? Note that in all graphs the horizontal axis (x axis) is time, the vertical axis (y axis) is number of homicides, and the • indicates an observation.
a.

m2stgide_f01_files/i0400000.jpg
b.

m2stgide_f01_files/i0400001.jpg
c.

m2stgide_f01_files/i0400002.jpg
d.

m2stgide_f01_files/i0400003.jpg
e.
none of the above
 

37. 

For a spurious relationship to occur, which of the following condition(s) is (are) required?
a.
The partial relationships must be significantly less than the original.
b.
The test variable must be antecedent to the dependent variable.
c.
The test variable must be antecedent to the independent variable.
d.
All of the above are correct.
e.
Only a and c are correct.
 

38. 

According to the following model,

X®Y®Z
a.
X is the dependent variable.
b.
X is the independent variable.
c.
Z is the independent variable.
d.
X is the intervening variable.
e.
Y is the dependent variable.
 

39. 

Using following model,

X®Y®Z

which of the following statements is (are) FALSE about Y?  Y is the
a.
test variable
b.
intervening variable
c.
antecedent variable
d.
Y helps us interpret the relationship between X and Z
e.
all of the above are TRUE about Y
 

40. 

Suppose we observed that the more firefighters there were at a fire site, the greater the amount of fire damage. Suppose we also observed that the size of the fire was related to both the amount of damage and the number of firefighters present. In this case, we would call size of fire the
a.
independent variable
b.
dependent variable
c.
intervening test variable
d.
antecedent test variable
e.
cannot tell from the information given
 

41. 

The difference between interpretation and explanation is
a.
a logical difference
b.
a statistical difference
c.
that the partials are reduced in explanation but not in interpretation
d.
that the partials are reduced in interpretation but not in explanation
e.
all of the above
 

42. 

You notice a positive relationship between the number of children in a family and father's occupational prestige. When you control for mother's occupational prestige, the partials become negative in sign. This illustrates
a.
specification
b.
a distorter variable
c.
a suppressor variable
d.
explanation
e.
interpretation
 

43. 

An example of multivariate analysis would be
a.
an examination of the ages of all women who are corporate executives
b.
an analysis of the relationship between age, sex, and type of nightspot frequented in a given city in the Midwest
c.
an analysis of the relationship that exists between types of undergraduate major and positions held in business
d.
an analysis of the relationship between type of offense and length of prison sentence for those who had a jury trial
e.
all of the above
 

44. 

In reading a table that someone else has constructed, the rule of thumb is
a.
if the table is percentaged down, read across, and if the table is percentaged across, read down
b.
if the table is percentaged down, read down
c.
if the table is percentaged across, read across
d.
all of the above
e.
only b and c are correct
 



 
Check Your Work     Reset Help