SAMPLE EXAM QUESTIONS FOR RESEARCH METHODS

1. Which of the following would be an example of applied research?
A. research to satisfy intellectual curiosity
B. research on a problem in need of improvement *
C. research on whom citizens decide to vote for
D. research for theoretical purposes

2. Which of the following is the textbook definition of the word empirical?
A. consistent with common sense
B. contradictory to common sense
C. something that is "known" to be true
D. something grounded in observation and experience *

3. What does it mean when it is said scientific knowledge is transmissible?
A. it means the data was collected by a team of researchers
B. it means that scientific knowledge is nonnormative
C. it means that the research can be analyzed and replicated *
D. it means that original incorrect results can be made to correct themselves

4. Which of the following is NOT a building block of social scientific research?
A. induction *
B. hypothesis
C. concept
D. variable

5. Suppose a researcher hypothesizes that a person who favors national health insurance is more likely to vote for Bill Clinton. In this case, the dependent variable is:
A. attitude toward national health insurance
B. attitude toward Bill Clinton
C. Bill Clinton's support for national health insurance
D. presidential vote *

6. Which building block of research generally refers to how scientific knowledge is sharpened or made more precise?
A. induction
B. hypothesis
C. concept *
D. variable

7. Which of the following is the textbook definition of a hypothesis?
A. a statement proposing the relationship between two or more concepts
B. a statement proposing the relationship between two or more variables *
C. a statement consisting of an educated guess about some phenomenon
C. a statement that is empirically specific about some phenomenon

8. What type of validity is associated with how well the intended analysis is consistent with the design to be used?
A. statistical correspondence validity *
B. test-retest validity
C. criterion validity
D. convergent validity

9. An association between two variables (like marked crosswalks and pedestrian accidents) implies that one variable is the cause of the other.
A. True
B. False *

10. Representativeness is what one is after with interpretation, and generalizeability is what one is after with sampling.
A. True
B. False *

11. Which of the following is an example of a delimitation in a study of marijuana use among college students at traditional, four-year, liberal arts institutions?
A. Use of marijuana among college students may or may not be decreasing
B. Marijuana use may vary among college students depending upon type of institution
C. The typical, 18-24 year old college student may be using less marijuana nowadays
D. Young, 18-24 years olds may be using less marijuana *  

12. Researchable questions are necessarily narrow and specific.
A. True *
B. False

13. An experiment is the best research strategy for investigating the causes of phenomena.
A. True *
B. False

14. Which of the following is NOT an example of a scientific research question?
A. Why is capital punishment legal in some states and not in others?
B. How are attitudes toward abortion related to religious affiliation?
C. Should intelligence be valued over physical prowess? *
D. Is involvement in crime related to social class?

15. The difference between explanation and prediction in science is that:
A. predictions are testable; explanations are not
B. predictions involve logical deduction; explanations involve logical induction
C. explanations refer to the past or present; predictions refer to the future *
D. explanations have been empirically verified; predictions have not

16. What type of hypothesis is usually involved in confirmatory research?
A. associated
B. directional
C. nondirectional
D. magnitude *

17. Which group of terms are most synonymous or logically equivalent?
A. law, fact, empirical generalization
B. law, hypothesis, empirical generalization *
C. concept, hypothesis, theory
D. concept, hypothesis, law

18. Which group of terms is ordered from most to least general?
A. law, fact, theory
B. fact, law, theory
C. theory, fact, law
D. theory, law, fact *

19. The scientific process:
A. always begins with theory and ends with research
B. involves a continuous interaction of theory and research *
C. always starts with research, out of which theories are built
D. is an orderly procedure for making systematic observations

20. The researcher must precisely formulate the null hypothesis whenever doing research.
A. True
B. False * 

21. Which of the following lists is a set of variables?
A. male, Protestant, year in college
B. architect, engineer, lawyer
C. income, Democrat, age
D. religious affiliation, gender, years of schooling *

22. It is hypothesized that among the elderly, there is a relationship between marital status and happiness. In this hypothesis, happiness is a(n) __________ variable and marital status is a(n) ___________ variable while age is a(n) ________ variable.
A. independent, dependent, control
B. independent, control, dependent
C. dependent, independent, control *
D. dependent, control, independent

23. Criminologist Travis Hirschi found that 19% of boys compared with 7% of girls report they had stolen something worth between $2 and $50. This indicates that there is _______________ between gender and self-reported theft.
A. no association
B. an association *
C. a linear relationship
D. a curvilinear relationship

24. If older people are less likely to attend church than younger people, the relationship between age and church attendance is:
A. positive
B. negative *
C. curvilinear
D. symmetric

25. A correlation coefficient of .10 between SAT score and college GPA indicates:
A. a weak association *
B. a strong association
C. a statistically significant association
D. both b and c

26. A nonspurious relationship implies that:
A. there is a noncausal association between the variables
B. there is a positive association between the variables
C. there is a negative association between the variables
D. there is a causal link between the variables *

27. Which of the following is the best statement of a hypothesis?
A. Social class is related to party affiliation
B. Among the elderly, marital status is related to happiness
C. Women are more likely to oppose pornography than men *
D. Political conservatives support authoritarian leaders

28. Which of the following is the worst statement of a hypothesis?
A. The greater the social distance between victim and criminal, the more severe the punishment
B. Women tend to receive less pay than men for the same work
C. Men are usually less religious than women
D. Happiness is related to intelligence *

29. An independent variable in one study may be a dependent variable in another study.
A. True *
B. False

30. A scientifically sound hypothesis can be stated properly in several different ways.
A. True *
B. False

31. What does a null hypothesis usually do?
A. make an uneducated guess about the nature or direction of a relationship
B. state that there is an indirect relationship between the variables
C. suggest an inverse relationship between the variables
D. posit the absence of a relationship between the variables *

32. What type of hypothesis proposes a relationship between two variables without specifying the nature of that relationship?
A. directional
B. correlative *
C. causal
D. logarithmic

33. What type of measurement device presents respondents with increasingly difficult measures of approval for an attitude and also provides a no opinion midpoint?
A. Likert scale
B. Guttman scale *
C. Thurstone scale
D. Shapiro scale

34. Which of the following is the best example of an operational definition?
A. group solidarity: the strength of positive interpersonal relations within a group
B. political participation: voluntary taking part in choosing political leaders
C. delinquency: any person between the ages of 7 and 18 who admits to a crime *
D. anomie: a state of normlessness in which social control has become ineffective

35. A variable's level of measurement indicates the:
A. number of questions used to measure the variable
B. number of categories which can be used to group scores on the variable
C. kinds of comparisons that can be made between cases in different categories *
D. correspondence between conceptual and operational definitions

36. What would be a minimally adequate sample size for a city with a population of 60,000?
A. 1% *
B. 5% 
C. 10%
D. 15%

37. Which of the following is an example of nominal level measurement?
A. family size (number of children in a family)
B. political participation (number of times voted in last 10 years)
C. educational attainment (highest year or grade in school completed)
D. political party affiliation (Republican, Democrat, Independent, Other) *

38. Suppose a survey item asks someone if something is very important, somewhat important, not very important, or unimportant. This is an example of what level of measurement?
A. nominal
B. ordinal *
C. interval
D. ratio

39. Which level of measurement has an absolute or "true" zero point?
A. nominal
B. ordinal
C. interval
D. ratio *

40. What level of measurement do most inferential statistics rely upon?
A. nominal
B. ordinal
C. interval *
D. ratio

41. Reliability is mostly a matter of _________, while validity is mostly about _____.
A. consistency; accuracy *
B. accuracy; consistency
C. similarity; dissimilarity
D. similarity; consistency

42. It is possible for a measure to be reliable but not valid.
A. True *
B. False

43. It is possible for a measure to be valid but not reliable.
A. True
B. False *

44. If all the variation in a measurement is due to true differences in the concept, then the measures would be perfectly reliable and valid.
A. True *
B. False

45. Which term would best refer to bias in selection of experimental and control groups?
A. unsystematic random assignment
B. experimental group mortality
C. maturation or decay
D. selection error *

46. What is the most appropriate research design to study, for example, how effective mandatory seat belt laws have been in reducing automobile accident deaths?
A. cross sectional
B. factorial
C. experimental
D. time series

47. The key feature of probability sampling is:
A. selection of very large samples
B. elimination of sampling error
C. random selection *
D. reduction of bias in the sampling frame

48. Parameter is to _________ as statistic is to ____________.
A. measurement; sampling
B. population; sample *
C. mean; standard error
D. standard error; mean

49. In general, the larger the sample, the smaller the:
A. disproportionality
B. sampling proportion
C. size of the strata
D. sampling error *

50. The accuracy of a sample is expressed in terms of margin of error and ________.
A. validity
B. reliability
C. confidence level *
D. proportionality

51. What technique can be used to make a disproportionate sample representative?
A. clustering
B. snowballing
C. weighting *
D. post hoc randomization

52. What type of probability sampling would oversample some types of people in the population?
A. simple random
B. stratified random *
C. systematic random
D. cluster

53. What type of nonprobability sampling would involve a captive audience?
A. quota
B. convenience *
C. purposive
D. snowball

54. Since a normal curve is symmetrical, we know that ____ of the cases for scores on any variable lie between the mean and plus or minus ONE standard deviation.
A. 33.3%
B. 50%
C. 65% *
D. 95%

55. Since a normal curve is symmetrical, we know that ____ of the cases for scores on any variable lie between the mean and plus or minus TWO standard deviations.
A. 33.3%
B. 50%
C. 65%
D. 95% *

56. To estimate the mean of the population from sample information, we need to calculate the standard deviation of the distribution of the sample means around the population mean. This is done by dividing the standard deviation of our sample by the square root of N, and is called the:
A. central limit
B. integral calculus
C. standard error *
D. Z score

57. Defining the outcome variable, as in what type of crime to study, is what part of the measurement process?
A. conceptualization *
B. operationalization
C. selection
D. mono-operationalization

58. What threat to validity or reliability exists when research subjects drop out of the experiment?
A. diffusion
B. history
C. mortality *
D. maturation

59. Which of the following is the most difficult validity to achieve?
A. face
B. content
C. criterion
D. construct *

60. The Kuder-Richardson coefficient, or KR-20, comes closest to what type of reliability?
A. test-retest
B. multiple forms
C. split-half *
D. inter-rater 

61. What percentage of people taking a test should be "suckered" into guessing a distracter response is the correct answer?
A. 2% *
B. 4%
C. 6%
D. 8%

62. What percentage of people taking a test are sorted in the best and worst groups for purposes of constructing a difficulty or discrimination index?
A. 12%
B. 18%
C. 27% *
D. 33%

63. Which of the following is most likely an item coming from a scale and not an index?
A. I have committed three armed robberies in the last year
B. I experimented with drugs as a juvenile
C. I believe that authority figures should be challenged
D. I tend to treat others as they treat me *

64. The notion of "tipping points" in social science research is most closely associated with what type of measuring instrument?
A. test
B. scale *
C. index
D. questionnaire

65. Which of the following is the most commonly used type of scale in most social science research?
A. Thurstone
B. Likert *
C. Guttman
D. Semantic Differential

66. Scales are primarily used to predict outcomes while indexes are primarily used to explore causes.
A. True *
B. False

67. Which of the following statements best characterizes the attitude of most researchers toward the techniques of factor and cluster analysis?
A. They have the same utility as computing validity and reliability coefficients
B. Their shortcomings are overcome by the way they validate item measurement
C. They are best seen as computer-assisted data runs that may or may not be worthless *
D. These techniques require a computer proficiency far beyond the average researcher 

68. Which statistic relies upon information provided in a crosstab to tell if a relationship is statistically significant and that we can reject the null hypothesis?
A. chi-square *
B. ANOVA
C. Pearson's correlation coefficient
D. R-squared

69. ANOVA and/or the difference of means test is typically used whenever:
A. the number of observations exceed ten thousand
B. the sampling distribution doesn't coincide with the normal distribution
C. observed and expected tables are quite different in the crosstab
D. the independent variable is nominal or ordinal and the dependent one is interval or ratio *

70. Pearson's correlation coefficient can be calculated for any regression line.
A. True *
B. False

71. Which of the following is NOT a consideration in deciding to use an experimental design?
A. precise categorization
B. randomization
C. ethics
D. psychodynamics *

72. The Hawthorne Effect occurs primarily with control group subjects while the Placebo Effect occurs primarily with experimental group subjects.
A. True
B. False *

73. What are control groups called in quasi-experiments?
A. contrast
B. comparison *
C. concomitant
D. converse

74. What is usually the independent variable in a noninterrupted time series analysis?
A. context
B. history
C. time *
D. maturity

75. Which technique of causal modeling involves narrowing the dependent variable?
A. subclassification
B. elaboration
C. crosstabulation
D. specification *

76. Which type of longitudinal design would be seen in a study entitled Growing Up Deviant using samples from 1954, 1976, and 1998?
A. cross-sectional
B. trend
C. cohort *
D. panel

77. A typical cross-national research study would have about how many survey respondents per nation?
A. 500
B. 1000 *
C. 2000
D. 3000

78. Which type of interview would least restrict the topics of conversation?
A. unstructured *
B. structured
C. semistructured
D. anti-structured

79. Which of the following is NOT considered an inherent weakness of survey research?
A. reactivity
B. nonresponse rate
C. measurement error
D. exploration rather than explanation *

80. Which of the following is NOT one of the ways to increase response rate for a questionnaire?
A. attractive cover letter
B. timing
C. visits *
D. renumeration

81. What type of survey research method would be most appropriate for studying inmates on death row shortly before their scheduled executions?
A. cross-sectional questionnaire *
B. panel interviews
C. unstructured interviews
D. probability-based questionnaire

82. Probes are used primarily in questionnaires rather than interviews.
A. True
B. False *

83. What area of statistics deals mostly with parametrics?
A. frequentism
B. descriptive
C. relational
D. inferential *

84. Which measure of central tendency would be appropriate if you had mostly extremely high scores and extremely low scores on some item measured at the ratio level?
A. mean
B. median
C. mode *
D. octal

85. The square root of the variance as a measure of dispersion is always the:
A. half variance
B. median
C. z-score
D. standard deviation *

86. How do you calculate the coefficient of alienation?
A. multiply the standard deviation by the mean
B. square the correlation coefficient
C. subtract the coefficient of determination from one *
D. add the KR-20 coefficient to the square root of the sample size minus one

87. Which group of inferential statistics make the most use of two-tailed tests of significance?
A. F-tests
B. T-tests *
C. W-tests
D. Z-tests

88. Which type of qualitative researcher role is most likely to involve "going native?"
A. complete participation *
B. participant as observer
C. observer as participant
D. complete observation

89. Which type of qualitative research mostly involves grounded theory?
A. dramaturgy
B. ethnography
C. participant-observation
D. all of the above *

90. Which type of qualitative research is considered to have the least reactivity involved?
A. case study
B. sociometrics
C. unobtrusive measures *
D. natural experiment

91. The Q-sort technique is to Meta-analysis as microscopic is to macroscopic.
A. True *
B. False

92. What part of research ethics goes as far back as the Nuremberg Code?
A. voluntary consent *
B. benefits should outweigh harm
C. freedom to withdraw at any time
D. equitable distribution of benefits and burdens

93. With federally-funded research, a researcher can be held liable for harm, but not for libel or slander.
A. True
B. False *

94. In research ethics, confidentiality should be guaranteed if the researcher cannot promise anonymity.
A. True *
B. False

95. Which of the following is NOT a limitation on research involving inmates, under federal guidelines?
A. promises of leniency at parole
B. placing a statement of cooperation in their file
C. eliciting cooperation by saying the research is innovative *
D. subjecting to treatment below minimal standards of confinement

96. Which type of policy-oriented research most involves the chance of re-establishing agency priorities?
A. cost-benefit analysis
B. feasibility analysis
C. needs assessment *
D. organizational development

97. Program evaluation, as opposed to policy analysis, is normally done when policy is fixed and unchangeable.
A. True *
B. False

98. Feedback loops usually exist in organizations between behavior and what other item in program evaluation?
A. mission
B. goals *
C. objectives
D. results

99. What step of program evaluation most likely involves triangulation?
A. Hypothesis
B. Sampling
C. Design *
D. Interpretation

100. What step of policy analysis mostly likely involves determining the public interest served by the agency?
A. Problem Identification *
B. Criteria Selection
C. System Assessment
D. Feasibility Assessment

Last updated: Oct 09, 2006
Not an official webpage of APSU, copyright restrictions apply, see Megalinks in Criminal Justice
O'Connor, T.  (Date of Last Update at bottom of page). In Part of web cited (Windows name for file at top of browser), MegaLinks in Criminal Justice. Retrieved from http://www.apsu.edu/oconnort/rest of URL accessed on today's date.