Exam Questions Measurement Chapter 4

Chapter 04

1. When we conceptualize, we specify what we mean by a term.

a. True

b. False

2. A concept that does not vary is known as a constant.

a. True

b. False

3. The term variable may be used interchangeably with the term indicator.

a. True

b. False

4. Interrater Reliability is a useful measurement tool when the researcher is interested in assessing the degree to which the ratings reflect the reality that was being measured.

a. True

b. False

5. Face validity is less difficult to discern than content validity.

a. True

b. False

6. Low levels of internal consistency are better as they demonstrate that the scale has individual questions addressing all the areas of interest for the researcher.

a. True

b. False

7. Systematic error may occur without the knowledge of the researcher. It is also not always a reflection of a problem with the researcher him/herself.

a. True

b. False

8. An operation is the process of linking abstract concepts to empirical indicants.

a. True

b. False

9. Depression is an example of a concept with multiple dimensions.

a. True

b. False

10. Scales are used to lessen problems of idiosyncratic variation in responses to single question indicators.

a. True

b. False

11. Experienced researchers are capable of gathering data without any systematic or random error.

a. True

b. False

12. A scale is formed by using several questions to measure one concept and summing or averaging responses.

a. True

b. False

13. Triangulation weakens measurement considerably because we can achieve similar results with different measures of the same variable.

a. True

b. False

14. Gender is a good example of an interval level of measurement.

a. True

b. False

15. Researchers engaged in qualitative researcher don’t know as much about their research subjects and topics before they begin researcher as those engaged in quantitative research.

a. True

b. False

16. Unlike other levels of measurement, nominal levels of measurement need not be exhaustive and mutually exclusive.

a. True

b. False

17. For most statistical analyses in social work research, the interval and ratio levels of measurement can be treated as equivalent.

a. True

b. False

18. At the ratio level of measurement, addition and subtraction are possible.

a. True

b. False

19. Reliability is a prerequisite for measurement validity

a. True

b. False

20. The administration of a scale to a research participant while he or she is engaged in two tasks simultaneously allows us to measure concurrent validity.

1. True

b. False

21. Validity is the process by which the potential participant is given all the information they need to decide whether to participate in the study.

a. True

b. False

22. Match the key term to its definition.

[c] 1. Concept

[a] 2. Conceptualization

[d] 3. Operationalization

[b] 4. Measurement

[e] 5. Operation

a. The process of specifying what we mean by a term.

b. The process of linking abstract concepts to empirical indicants.

c. A mental image that summarizes a set of similar observations.

d. The process of specifying the operations that will indicate the value of cases on a variable.

e. The procedure for identifying or indicating the value of cases on a variable.

23. Match the key term to its definition.

[b] 1. Face validity

[e] 2. Content validity

[a] 3. Criterion validity

[c] 4. Concurrent validity

[d] 5. Predictive validity

[f] 6. Construct validity

a. The results of one measure match those obtained with a more direct or an already validated measure of the same phenomena.

b. A measure obviously pertains to the meaning of the concept being measured more than to other concepts.

c. A measure is validated by being closely related to a criterion conducted at the same time.

d. A measure is validated by predicting scores on a criterion measured in the future.

e. A measure covers the full range of a concept's meaning.

f. A measure is validated by relating to other measures specified by a theory.

24. Match the key term to its definition.

[a] 1. Test-Retest Reliability

[b] 2. Interitem Reliability

[d] 3. Inter-Observer Reliability

[c] 4. Alternate Forms Reliability

a. Testing unchanging phenomenon at two different times.

b. The association of answers to a set of questions designed to measure the same concept.

c. Comparison of subjects' answers to slightly different versions of survey questions.

d. Correspondence between measures made by different observers.

25. The process by which a researcher defines specifically what he or she means when using a concept is known as:

a. Conceptualization

b. Operationalization

c. Generalization

d. Reliability

e. Specification

26. The procedures for identifying or indicating the value of cases on a variable is known as:

a. Concepts

b. Conceptualizations

c. Operations

d. Operationalizations

e. Indicators

27. To reduce idiosyncratic variation in responses to individual questions, social work researchers use:

a. Test-retest reliability

b. Alternate forms reliability

c. Scales

d. Preexisting questions

e. Ratio levels of measurement

28. Comparing a set of responses to depression and anxiety scales would allow one to determine whether which of these types of validity is present:

1. Known-groups validity
2. Convergent validity
3. Concurrent validity

d. Discriminant validity

29. If a scale is able to measure multiple aspects of a given concept, it is known as a:

a. Multidimensional scale

b. Attitudinal index

c. Guttman scale

d. Reliability measure

e. None of the above

30. In variables measured at the nominal level of measurement:

a. Rankings are possible

b. Addition and subtraction are possible

c. Multiplication and division are possible

d. Ratios are meaningful

e. Values measure kind but not quantity

31. Although few true interval-level measures exist in the social sciences, which of the following is likely to be treated as one?

a. Scales

b. Ratios

c. Collapsed categories of highly specific variables, such as income

d. Anchor points in a ranking system

e. Dichotomies

32. Which of the following can NOT be performed on data collected at the ratio level of measurement?

a. Addition/subtraction

b. Greater than/less than

c. Multiplication/division

d. Ratios

e. All of the above can be performed on ratio level data.

33. A variable that has only two values is known as a/an:

a. Alpha

b. Dichotomy

c. Index

d. Scale

e. Measure

34. What kind of validity is achieved if scores on measures related to one concept are not strongly associated with measures of different concepts?

a. Face validity

b. Criterion validity

c. Content validity

d. Discriminant validity

e. Predictive validity

35. Which of the following statistics is used commonly to measure inter-item reliability?

a. Pearson’s r

b. Cronbach’s alpha

c. Guttman’s scale

d. Betas

e. Reliability measures

36. Inter-observer reliability occurs when:

a. Different observers measure the same phenomena in the same way

b. Different observers agree on a definition of measurement

c. Different observers administer an instrument

d. Different observers contribute to the conceptualization process

e. Different observers measure some phenomena concurrently

37. When conducting a survey, researchers may often create two versions of the questionnaire. They may vary the order of the questions or slight wording of the questions. They then divide the sample into two equal sub-samples and administer each version. When surveys are collected, answers on the two different questionnaires are compared to determine:

a. Test-Retest reliability

b. Criterion validity

c. Alternate-forms reliability

d. Construct validity

e. Content validity

38. When researchers measure an unchanging phenomenon at two different times, the degree to which the two measurements are related is called:

a. Test-Retest reliability

b. Criterion validity

c. Predictive validity

d. Inter-item reliability

e. Alternate-forms reliability

39. Reliability refers to which of the following?

a. A measurement captures what it intends to measure

b. A measurement includes all dimensions of a concept

c. A measurement is free of error

d. A measurement is based on empirical reality

e. A measurement yields consistent scores

40. When Danette Hann, Kristen Winter, and Paul Jacobsen (1999) compared subject scores on the CES-D to a number of indicators that they felt from previous research and theory should be related to depression: fatigue, anxiety, and global mental health, they were hoping to establish which of the following?

a. Face validity

b. Content validity

c. Criterion validity

d. Predictive validity

e. Construct validity

41. Predictive validity occurs when:

a. A measure can predict scores on a criterion measured in the past.

b. A measure relates to other measures specified in a social theory.

c. A measure is associated with a criterion collected at the same time.

d. A measure can predict scores on a criterion measured in the future.

e. A measure is operationalized as a variable.

42. To establish concurrent validity, a researcher must include which of the following in a survey that includes a new index of depression?

a. A system for weighting responses

b. Multiple forms of the same index

c. A previously validated measure of depression

d. Single items and matrix questions

e. Open-ended questions that ask for details about responses

43. Face validity refers to:

a. The ability of subsets of items to predict one another

b. The strength of items to predict one another

c. The apparent appropriateness of how a concept is measured

d. The likelihood that multiple indicators measure the same phenomenon

e. The ability of indicators to predict desired outcomes

44. Which level of measurement is the most mathematically precise?

a. Interval

b. Nominal

c. Ordinal

d. Ratio

e. All levels of measurement are equally precise

45. Which of the following is an example of a variable measured at the interval level of measurement?

a. Age in years

b. Income in dollars

c. Temperature in degrees Fahrenheit

d. Acres of land planted in food crops

e. None of the above are measured at the interval level

46. Which of the following is an example of a variable measured at the ordinal level of measurement?

a. Military rank

b. Birth order of siblings

c. Age measured as child, teen, adult, and elderly

d. Order in which subjects complete a given task

e. All of the above are measured at the ordinal level

47. Which of the following is an example of a variable measured at the nominal level of measurement?

a. Location in which respondent was born

b. Religiosity measured as not religious, somewhat religious, and very religious

c. Time in seconds in which a subject completes a given task

d. Number of respondents’ first cousins

e. Level of education in years completed

48. If every case can be classified as having only one attribute, we say that attributes are:

a. Exhaustive

b. Mutually exclusive

c. Operationalized

d. Reliable

e. Valid

49. Using more than one measure of the same variable, such as using a survey and direct observation, is known as:

a. Validation

b. Reliability

c. Conceptualization

d. Triangulation

e. Operationalization

50. The process of specifying the operations that will indicate the value of cases on a variable is known as:

a. Conceptualization

b. Criterion validity

c. Construct validity

d. Operationalization

e. Triangulation

51. Explain the difference between concepts, conceptualization, and operationalization using the example of the concept of honesty.

52. What are the advantages and disadvantages of using single questions rather than question sets to measure concepts?

53. Develop a conceptual definition of antisocial behavior, making certain to consider the potential dimensions of the concept (and therefore construct validity). Write an index that measures this concept with closed ended questions.

54. What is the difference between conceptualization and operationalization? After defining these terms, demonstrate this difference by conceptualizing and operationalizing one of the following concepts: happiness, prejudice, deviance, environmentalism, justice, poverty. Discuss potential measurement procedures for the concept in depth.

55. Construct a short survey of five questions designed to measure attitudes about gay couples adopting children. At least one question must be open ended, one must be closed-ended, and three or more questions must form an index or a scale. Discuss an alternative procedure to measure these attitudes, and how the survey would compare with this alternative procedure in terms of validity.

56. The book states that it is important to try to always measure one’s variables at the highest level possible. Why is this the case? How would you decide on the “highest possible level” when preparing to being the data collection process?

57. Detail the strengths and weaknesses of gathering each type of data. Is it easy to gather? Is it difficult to decipher? How well would it fit the research interests you could be pursuing?

58. Propose measures of student satisfaction at the nominal, ordinal, and interval and ratio levels. Discuss the advantages and disadvantages of these measurement approaches. Suggest procedures for establishing validity and reliability of all of your satisfaction measures. Explain your rationale for each procedure.