What Is Convergent Validity? | Definition & Examples
Convergent validity is one way to demonstrate the validity of a test—whether it’s measuring the thing it’s supposed to. Specifically, convergent validity evaluates whether a test matches other tests of similar constructs.
If two tests are measuring the same thing, their results should be strongly correlated. This strong correlation indicates convergent validity, which in turn provides evidence of construct validity.
They compare the results of their form to a survey that measures emotional regulation, as they expect this construct to closely relate to distress tolerance.
A high correlation between their form and the existing survey indicates convergent validity.
What is convergent validity?
Convergent validity is whether a test or instrument provides results similar to a test that measures the same or a similar construct. A construct is simply any phenomenon that cannot be directly measured. Fields like psychology often involve the study of constructs, such as emotion or intelligence.
If a test is measuring what it’s supposed to, its results should match (or converge with) those of other tests that measure related constructs. Researchers can therefore validate a new measure by comparing it to other, theoretically related measures. If the results of both measures are strongly correlated, convergent validity has been established.
Convergent validity is one form of evidence for construct validity—an overall assessment of whether a test is measuring what it’s supposed to. Other types of validity include face validity, content validity, criterion validity, and discriminant validity.
Convergent validity example
Consider the following example of how convergent validity might be assessed in psychology research.
The researcher believes that willingness to try new foods should be related to openness to new experiences. They therefore compare the results of their survey to an existing scale of openness.
The researcher finds that there is only a weak correlation between their survey and openness to new experience, which indicates that their survey lacks convergent validity. They therefore decide to redesign the survey to make it more age-appropriate, with the aim of improving the survey’s sensitivity to food preferences in children, before reevaluating convergent validity.
Convergent vs discriminant validity
Convergent validity assesses whether a test or instrument provides results that are close to other measures of a similar construct. Discriminant validity (also referred to as divergent validity) assesses whether a test provides results that differ from tests of unrelated constructs.
It’s important to make sure a test is measuring what it’s supposed to, but it’s also helpful to ensure that a test isn’t measuring unrelated phenomena. A test that is sufficiently sensitive to a certain construct shouldn’t be providing information about something unrelated.
Consider the following example to better understand how convergent and discriminant validity can be determined.
To assess this test’s convergent validity, you should compare its results to a test of a similar construct. Someone’s self-control should be related to their ability to inhibit behavior, so you could determine convergent validity by computing the correlation between the self-control test and an existing measure of behavioral inhibition.
If both tests have similar results (i.e., are strongly correlated), you can conclude that your test has convergent validity.
To determine discriminant validity, you would instead want to compare your test to a test of something completely different. There should be no overlap between someone’s creativity and their self-control, so comparing your test results to a creativity test would allow you to assess discriminant validity.
If there is a weak (or non-existent) correlation between your test and a creativity test, you could conclude that your test has discriminant validity.
Establishing both convergent and discriminant validity is important in ensuring the construct validity of a measure.
How to measure convergent validity
Determining convergent validity involves several steps.
Step 1: Choose a similar test
To properly measure convergent validity, you must select a second test to compare your measure to. This second test should measure a construct that is theoretically related to whatever your own test is measuring.
Properly selecting this second test requires a strong understanding of the literature related to your construct. Consider how your construct relates to other topics, and use this information to select an appropriate test to compare to.
Step 2: Calculate the correlation between both tests
Once you’ve chosen a test to compare to, you must demonstrate that it provides similar results to your own. To do this, you can compute the correlation between the results of your test and the related one.
Pearson’s correlation is frequently used to compare two measures, provided its assumptions are met. This test provides a correlation coefficient, denoted r, that falls between -1 and 1. It is interpreted as follows:
- r = −1: perfect negative correlation between two variables
- r = 0: no correlation between two variables
- r = 1: perfect positive correlation between two variables
What is considered a “strong” correlation varies between fields. In addition to the strength of the correlation, you must also consider its statistical significance (generally, whether p < .05).
Consider, for example, a measure of self-control. Self-control is inversely related to impulsivity: someone with high self-control should have low impulsivity. We could therefore test the convergent validity of the self-control measure with a measure of impulsivity.
In this case, we would expect to see a negative correlation between the two measures. High scores on the self-control test should correspond to low scores on the impulsivity test and vice versa, demonstrating convergent validity
Frequently asked questions about convergent validity
- Why are convergent and discriminant validity often evaluated together?
-
Convergent validity and discriminant validity (or divergent validity) are both forms of construct validity. They are both used to determine whether a test is measuring the thing it’s supposed to.
However, each form of validity tells you something slightly different about a test:
- Convergent validity indicates whether the results of a test correspond to other measures of a similar construct. In theory, there should be a high correlation between two tests that measure the same thing.
- Discriminant validity instead measures whether a test is similar to measures of a different construct. There should be a low correlation between two tests that measure different things.
If a test is measuring what it is supposed to, it should correspond to other tests that measure the same thing while differing from tests that measure other things. To assess these two qualities, you must determine both convergent and discriminant validity.
- What is the difference between concurrent validity and convergent validity?
-
Convergent validity and concurrent validity both indicate how well a test score and another variable compare to one another.
Convergent validity indicates how well one measure corresponds to other measures of the same or similar constructs. These measures do not have to be obtained at the same time.
Concurrent validity instead assesses how well a measure aligns with a benchmark or “gold-standard,” which can be a ground truth or another validated measure. Both measurements should be taken at the same time.
- What is a construct?
-
A construct is a phenomenon that cannot be directly measured, such as intelligence, anxiety, or happiness. Researchers must instead approximate constructs using related, measurable variables.
The process of defining how a construct will be measured is called operationalization. Constructs are common in psychology and other social sciences.
To evaluate how well a construct measures what it’s supposed to, researchers determine construct validity. Face validity, content validity, criterion validity, convergent validity, and discriminant validity all provide evidence of construct validity.
