Key Takeaways
- Concurrent validity refers to the degree to which the results of a test accurately reflect reality or “correspondence with external criteria.”
- Concurrent validity is a type of criterion validity.
- This type of validity assesses whether a measure corresponds to another measure that has already been established as valid, such as medical diagnosis or educational achievement tests.
- Concurrent validity has a broad range of applications, ranging from measures of well-being to IQ and educational assessment tests.
What Is Concurrent Validity?
Concurrent validity measures the extent to which a measurement is confirmed by a related measurement. It is a type of criterion-related validity that compares the test results to observations or measurements from other tests, surveys, or assessments (American Psychological Association).
An example of concurrent validity would be comparing survey responses to a personality inventory with ratings given by supervisors at work.
If both sources yield similar results, then the measure being tested has strong concurrent validity.
Additionally, using a new interview process and seeing if it produces similar results as an older established process can also help demonstrate concurrent validity.
In general, any correlation between two related measures taken at the same point in time can be used to demonstrate concurrent validity.
Concurrent validity is especially important when measuring variables that have been malleable over time or are difficult to observe directly.
For example, a personality assessment may be compared to criteria such as how much people like the person taking the test or how well they work with others to determine its concurrent validity.
Additionally, it can also provide useful information about a new measurement tool’s accuracy when compared to an established one.
How to measure concurrent validity
Measuring concurrent validity involves looking at correlations between two related measures taken at nearly the same time.
The resulting correlation is a concurrent validity coefficient. For example, teachers may create a mathematics test that students can take in lieu of the respective course.
In other words, students would be permitted to pass a test instead of taking a course if the test scores could be used to accurately predict the current performance of students in the course.
To determine concurrent validity, students completing a mathematics course take an arithmetic achievement test.
The arithmetic achievement test is acceptable for use if there is a strong connection between the grades of the arithmetic achievement test and the mathematics course (Gregory, 2000).
Examples of concurrent validity
Depression Questionnaires
Depression is a common mental health issue that affects many people, so it is important to assess its severity accurately.
One way of doing this is through the use of depression questionnaires. In this context, concurrent validity involves comparing scores on the questionnaire with scores from other measures that should be related, such as clinician-rated symptom scales or diagnostic interviews based on DSM criteria.
This allows researchers to determine whether higher scores on the questionnaire correlate with higher scores on these other measures and vice versa, providing evidence of concurrent validity for the questionnaire (Bowers, 2004).
IQ Tests
IQ tests are widely used to measure intelligence, but they must first demonstrate concurrent validity before they can be relied upon as accurate.
Numerous circumstances affect the accuracy of IQ tests over time. For example, researchers have established that the average IQ score of test takers increases by three points every decade.
Since IQ is designed to be a fundamentally curved scale, using concurrent validity as a way of confirming new means is essential to its usability. There are many ways that researchers can ensure the concurrent validity of IQ tests.
For example, researchers can measure whether students’ scores on an IQ test are positively correlated with their grades in school. Otherwise, they may test if the calculated IQ scores of their assessment correlate with the calculated IQ scores of others (Hays et al., 2002).
Quality of Life Research
One example of concurrent validity could involve a self-report measure of quality of life, the Satisfaction with Life Domains Scale for Cancer (SLDS-C), being verified by its score correlation of 0.76 with another cancer-specific quality of life measure, the Functional Assessment of Cancer Therapy Scale-General (FACT-G).
These two scales both measure functional well-being, emotional well-being, and physical well-being.
Because there is a strong correlation between these subscales, researchers can better assume that those with higher life satisfaction are predicted to express more positive affect and have higher levels of health status (Baker et al., 2007).
FAQs
Is concurrent validity internal or external?
Internal validity is an indication of how well a research study has been conducted, while external validity is an indication of the extent to which the results of a study can be generalized outside of the specific context in which they were collected.
Concurrent validity refers to the degree to which scores on one measure (e.g., a test) are similar to scores on another measure (e.g., an observation). It is usually measured by looking at correlations between scores on different measures taken at the same time.
Therefore, concurrent validity is considered internal validity because it involves measuring within the same context and timeframe (Gregory, 2000).
Is concurrent and convergent validity the same?
Convergent and concurrent validity are similar but distinct. Convergent validity is the extent to which two different measures of the same construct agree with one another.
Concurrent validity, on the other hand, refers to the agreement between a measure and an existing criterion that has already been established as valid. This type of validity is used to evaluate new measures against established ones in order to determine their accuracy and reliability.
While convergent validity is largely comparative between different measures, concurrent validity compares a measure to a “gold standard” of a construct. Thus, convergent validity is a type of construct validity, while concurrent validity is a form of criterion validity (Gregory, 2000).
Is concurrent validity better than predictive validity?
Concurrent validity is similar to predictive validity, as both of these are correlations between a test and relevant criteria. They only differ in the time when these two tests are measured (McIntire & Miller, 2005).
Concurrent and predictive validity are tests that are of a similar level of utility, and their usage largely depends on circumstances.
To measure concurrent validity, researchers take test scores and criterion scores simultaneously to demonstrate the extent to which test scores correctly estimate an individual’s present condition on a relevant measure.
How do we measure the concurrent validity of a questionnaire?
A researcher can measure the concurrent validity of a questionnaire by comparing the results to an existing measure of the same construct or trait that has been established to be a reliable standard.
For example, if a researcher constructs a questionnaire that is designed to measure self-esteem, they could compare the results of their questionnaire to the scores obtained from an extremely established measure of self-esteem.
If there is a significant correlation between the two measures, then this suggests that the new questionnaire has concurrent validity. In addition, researchers can assess concurrent validity by examining whether respondents’ responses on different items within the same scale are consistent with one another.
This type of analysis can reveal whether questions are measuring what they are intended to measure and provide further evidence for concurrent validity as a faucet of criterion validity (Lin & Yao, 2014).
How can concurrency validity be improved?
The degree of concurrent validity in a study can be improved by implementing a number of best practices.
Firstly, researchers can ensure that the data used for concurrent review is complete and up to date.
Secondly, researchers can use design techniques that reduce the chance of conflicting updates from different sources.
Thirdly, researchers can consider implementing automated conflict resolution protocols if appropriate.
Fourthly, they can create standard operating procedures that are consistently followed and regularly reviewed to minimize errors in concurrent reviews.
Finally, documenting the results of each concurrent review can help identify areas where improvements could be made or conflicts avoided in future reviews.
By adhering to these principles, organizations can ensure that their concurrent reviews are conducted accurately and reliably (Lin & Yao, 2014).
References
American Psychological Association. (n.D.) Concurrent Validity. American Psychological Association Dictionary.
Baker, F., Denniston, M., Hann, D., Gesme, D., Reding, D. J., Flynn, T., & Kennedy, J. S. (2007). Factor structure and concurrent validity of the Satisfaction with Life Domains Scale for Cancer (SLDS-C). Journal of Psychosocial Oncology, 25(2), 1–17.
Bowers, A. (2004). Concurrent Validity Study of the Clinical Assessment of Depression with the Beck Depression Inventory. University of Kentucky.
Gregory, R. J. (2000). Psychological testing, history, principles, and applications (4th ed.). Allyn & Bacon.
Hays, J. R., Reas, D. L., & Shaw, J. B. (2002). Concurrent validity of the Wechsler abbreviated scale of intelligence and the Kaufman brief intelligence test among psychiatric inpatients. Psychological reports, 90(2), 355-359.
Drake, R. D., Rao, G. G., McIntire, D. D., Miller, D. S., & Schorge, J. O. (2005). The Incidence of GTD in Hispanic Women: A 20-Year Experience at Parkland Memorial Hospital. Obstetrics & Gynecology, 105(4), 119S.
Lin, W. & Yao, G. Concurrent Validity. In Michalos, A. C. (Ed.). (2014). Encyclopedia of quality of life and well-being research (pp. 311-1). Springer Netherlands.
