Chapter 13 – Measurement: Scaling, Reliability, Validity

1. What is the measurement level of the following question?

“What is your gross income per month? € ”

a. Non-metric.

b. Interval.

c. Ratio.

d. None of the above answers is correct.

2. “The measurement level on which a variable is measured is of great influence on the possibilities that a researcher has to further describe these variables and thereby also determines the value of the data.”

In light of this remark, indicate which of the following measurement levels provides the most valuable data for a variable.

a. Nominal.

b. Ordinal.

c. Interval.

d. Ratio.

3. A nominal scale is always dichotomous.

a. T

b. F

4. Temperature is a variable with an interval scale.

a. T

b. F

5. A sport shooter shoots from a distance of 10 meter 10 times on a cardboard. On this board the middle circle with 12 points has the highest value, and the outer circle with 1 point the lowest. Shooting next to the board yields 0 points. For every 10 shots the points are counted up to a total score. What scale has this total score if the shooter hits the board every time?

a. Nominal.

b. Ordinal.

c. Interval.

d. Ratio.

6. Which of the alternatives below is not an example of a ranking scale?

a. Paired comparison.

b. Forced choice.

c. Comparative scale.

d. Stapel scale.

7. About a scale (set of questions) it can be said that it is if it measures what it should be measuring.

a. Reliable.

b. Accurate.

c. Valid.

d. Consistent.

8. Interval and ratio variables are also called metric variables.

a. T

b. F

9. Which of the following alternatives is not an example of a ranking scale?

a. Paired comparison.

b. Forced choice.

c. Likert scale.

d. Comparitive scale.

10. About a scale (set of questions) it can be said that the indicates how well the measure taps the concept as theorized. Which word is missing?

a. Content validity.

b. Construct validity.

c. Criterion-related validity.

d. Stability.

11. A moderator can only be measured on a nominal level.

a. T

b. F

12. Construct validity ensures that the measure includes an adequate and representative set of items.

a. T

b. F

13. With face validity, the validity is not tested statistically.

a. T

b. F

14. How can content validity of a scale be determined?

a. A panel of experts judges the content validity of an instrument.

b. Different instruments that intend to measure the same concept, are correlated with each other.

c. Two variables that are respected not to correlate with each other, are correlated with each other.

d. Through correlation or regression it is found out to what extent a prediction done on the basis of the instrument really proves to be true.

15. How do we call the following scale type?

“Where in the Netherlands do you live? The South

The West

The North

The East

a. A category scale.

b. A forced choice scale.

c. A multidimensional scale.

d. A itemized rating scale.

16. When a researcher is concerned about the extent to which an instrument adequately measures a concept, he is concerned about:

a. Concurrent validity.

b. Construct validity.

c. Content validity.

d. Convergent validity.

17. Discriminant validity is the extent to which experts are of the opinion that an instrument measures what it intended to measure.

a. T

b. F

18. The following scale type is:

“Cold |___|___|___|___|___|___|___|___|___| Hot”

a. A likert-scale.

b. A semantic differential scale.

c. A numerical scale.

d. An itemized rating scale.

19. The assessment of the goodness of a scale relates to both the validity and reliability of this scale.

a. T

b. F

20. Cronbach’s alpha can only be used for metric variables.

a. T

b. F

21. Cronbach’s alpha can only be used when a variable is measured through several statements or questions.

a. T

b. F

22. Stability and consistency are both indicators of the reliability of a measure.

a. T

b. F

23. Concurrent validity is a form of construct validity.

a. T

b. F

24. “Indicate the order in which you prefer the following coke-labels. Give your favorite label a 1, the label that you prefer next a 2, and so on:

Coca Cola ­

Pepsi

Dr Pepper “

This is an example of:

a. A rating scale.

b. An itemized rating scale.

c. A ranking scale.

d. None of the above answers is correct.

25. “As the calibration or fine-tuning of a scale increases in sophistication, so does the power of the scale”. What is therefore the least powerful scale?

a. A nominal scale.

b. An ordinal scale.

c. An interval scale.

d. A ratio scale.

26. The difference between an interval and a ratio scale is that a ratio scale has an arbitrary zero point.

a. T

b. F

27. Temperature is usually measured on an interval scale.

a. T

b. F

28. With which allows us to calculate a mode, but not a median and a mean?

a. A nominal scale.

b. An ordinal scale.

c. An interval scale.

d. A ratio scale.

29. Which of the following scales is a ranking scale?

a. Paired comparison.

b. Semantic differential scale.

c. Numerical scale.

d. Stapel scale.

30. How pleased are you with your new cellphone?

“Extremely pleased 7 6 5 4 3 2 1 Extremely displeased”

a. A likert-scale.

b. A semantic differential scale.

c. A numerical scale.

d. An itemized rating scale.

31. About a scale (set of questions) it can be said that it is if it measures what it purports to measure.

a. Valid.

b. Reliable.

c. Accurate.

d. Consistent.

32. About a scale (set of questions) it can be said that the indicates how well the results obtained from the use of the measure fit the theories around which the test is designed.

a. Content validity.

b. Criterion-related validity.

c. Construct validity.

d. Stability.

33. Predictive validity is established when the scores obtained with two different instruments measuring the same concept are highly correlated.

a. T

b. F

34. Convergent validity indicates the ability of the measuring instrument to differentiate among individuals with reference to a future criterion.

a. T

b. F

35. The internal consistency of measures is indicative of the homogeneity of the items in the measure that tap the construct.

a. T

b. F

36. Cronbach’s alpha can only be used when a variable is measured through more than one statements or items.

a. T

b. F

37. In a reflective scale, the items (all of them!) are expected to correlate.

a. T

b. F

38. A reflective scale is used when a construct is viewed as an explanatory combination of its indicators.

a. T

b. F

39. The internal consistency of measures is indicative of the homogeneity of the items in the measure that tap the construct.

a. T

b. F