Let's talk about measure development. Psychologists make a great deal of money creating self-report measures (or surveys) on important variables. For instance, measures of depression symptoms ask respondents to rate how often they have experienced a symptom of depression in the past two weeks.

If one wishes to measure and make some money, it is not as simple as it seems. One must demonstrate that the measure is both reliable and valid.

Let's assume that a measure on "cool" (not cold, but trendy/hip) has been created, and all the style magazines are interested in paying for it. However, before receiving payment, one must demonstrate that the measure is valid and reliable. A research study can be conducted to assess the measure's reliability and validity.

To assess the measure's reliability, a test-retest approach can be used, where the same respondents are asked to complete the measure twice at different time points. The responses can then be compared to see if the measure produces consistent results over time.

To assess the measure's validity, a criterion-related validity approach can be used, where the responses on the measure are compared to a known criterion. For example, if the measure is supposed to assess "coolness," the responses on the measure can be compared to a criterion such as the number of followers on social media.

If the measure produces consistent results over time and is related to a known criterion, then it can be considered reliable and valid.