What Is Criterion Related Validity

Benchmark validity refers to how well the measurement of i variable can predict the response of another variable.

1 variable is referred to as the explanatory variable while the other variable is referred to as the criterion variable.

For instance, we might want to know how well some college entrance test is able to predict the first semester grade point average of students.

The entrance exam would be the explanatory variable and the benchmark variable would exist the showtime semester GPA.

Criterion validity

We want to know if it'southward valid to utilise this particular explanatory variable every bit a way to predict the criterion variable.

How to Measure Benchmark Validity

We typically measure out criterion validity using a metric like the Pearson Correlation Coefficient, which takes on value between -1 and 1 where:

-1 indicates a perfectly negative linear correlation between two variables
0 indicates no linear correlation between two variables
1 indicates a perfectly positive linear correlation between two variables

The further away the correlation coefficient is from zero, the stronger the association between the 2 variables.

For example, if we nerveless data on archway exam scores and showtime semester GPA for one,000 students and found that the correlation between the two variables was0.843 then this would mean the two variables are highly correlated.

In other words, students who score high on the archway exam likewise tend to earn high GPA'southward during their first semester. Conversely, students who score depression on the entrance exam tend to earn depression GPA'south during their first semester.

Types of Criterion Validity

There are two main types of benchmark validity:

one. Predictive Validity

The first type of criterion validity is known as predictive validity, which determines whether or not the measurement of 1 variable is able to accurately predict the measurement of some variable in the future.

The previous example of measuring a student'south higher entrance exam score and their offset semester GPA is an instance of measuring predictive validity because we measure out the two variables at dissimilar points in time.

In other words, we're trying to determine if the entrance exam score canpredict first semester GPA well.

Predictive validity example

2. Concurrent Validity

The second type of benchmark validity is known every bit concurrent validity, which measures two variables meantime (i.eastward. at the aforementioned fourth dimension) to come across if one variable is significantly associated with the other.

An case of this would be if a company administers some type of exam to see if the scores on the test are correlated with employee productivity.

Example of concurrent validity

The benefit of this approach is that we don't accept to wait until some point in the time to come to accept a measurement on the criterion variable we're interested in.