The extent to which performance on a measure is related to performance on the job is called validity. Validity is one of the most important criteria for evaluating the quality and usefulness of a selection measure, such as a test, an interview or an assessment center. A valid selection measure can accurately predict how well a candidate will perform on the job, based on their scores or ratings on the measure.
In this article, we will explain what validity is, how it can be measured and evaluated, and why it is important for both employers and employees. We will also provide some tips on how to improve the validity of your selection measures and how to avoid common pitfalls.
What is Validity?
According to Transtutors, validity is “the extent to which performance on the selection measure (i.e., the predictor) is associated with performance on the job”. In other words, validity tells us how well a selection measure can capture the essential aspects of job performance and differentiate between high and low performers.
There are different types of validity, depending on how the association between the selection measure and the job performance is established. The most common types are:
- Criterion-related validity: This type of validity is based on correlating the scores or ratings on the selection measure with an external criterion, such as supervisor ratings, productivity data or customer satisfaction scores. The higher the correlation, the higher the validity. Criterion-related validity can be further divided into concurrent validity and predictive validity, depending on whether the criterion is measured at the same time or at a later time than the selection measure.
- Content validity: This type of validity is based on evaluating the content and format of the selection measure and how well it reflects the knowledge, skills, abilities and other characteristics (KSAOs) required for the job. Content validity is usually assessed by subject matter experts (SMEs), such as job incumbents, managers or HR professionals, who judge whether the items or tasks on the selection measure are relevant and representative of the job.
- Construct validity: This type of validity is based on testing whether the selection measure measures what it claims to measure, i.e., a specific construct or trait that is relevant for the job. Construct validity is usually assessed by using statistical techniques, such as factor analysis or structural equation modeling, to examine how the items or tasks on the selection measure relate to each other and to other measures of similar or different constructs.
How to Measure and Evaluate Validity?
The most common way to measure validity is to calculate a validity coefficient, which is a numerical index that ranges from -1 to +1 and indicates the strength and direction of the relationship between the selection measure and the criterion. A positive validity coefficient means that higher scores or ratings on the selection measure are associated with higher levels of performance on the criterion, while a negative validity coefficient means that higher scores or ratings on the selection measure are associated with lower levels of performance on