Question 13

Measurement of what is intended

For a scale to be considered valid, it must measure what it is intended to measure. This means that the scale accurately reflects the construct it claims to assess.

A) Consistency of results over time

While consistency of results over time, known as reliability, is important for a scale, it does not alone determine validity. A scale could consistently yield the same results without accurately measuring the intended construct, which highlights that reliability is a separate issue from validity.

B) Agreement between different raters

Agreement between different raters, or inter-rater reliability, is also a component of reliability, not validity. A scale may show consistent ratings among different raters but may still fail to measure the actual construct intended, thus not fulfilling the criteria for validity.

C) Norming using a nationwide random sample

Norming a scale with a nationwide random sample is related to ensuring that the scale is applicable across diverse populations, but it does not guarantee that the scale measures what it is supposed to measure. Norming can enhance the applicability and fairness of a scale, yet it does not address the core issue of whether the scale is valid.

D) Measurement of what is intended

This option directly addresses the essence of validity. For a scale to be deemed valid, it must accurately measure the specific construct it aims to assess. This is the fundamental criterion that determines the validity of any measurement tool.

Conclusion

The requirement for a scale to be valid is that it must measure what it is intended to measure, which is encapsulated in option D. All other options, while relevant to the discussion of reliability and norming, do not directly address the need for the scale to accurately reflect its intended construct, thereby failing to establish validity.