Psychologists measure validity to find out what is actually measured
In psychology, validity (also known as test validity) describes how accurately a test or measure assesses the constructs (abstract concepts or attributes that are inferred from behavior and other indicators rather than direct observation) it is intended to measure. Psychologists make decisions based on the data collected by psychological assessments, tests, or measurements, and without understanding what the data represents, decisions get made using that data incorrectly, with real-world consequences. There are many types of validity that together establish the overall validity of a test or measure. This blog post explores validity in detail and demonstrates how and why we know that psychological tests and measurements work.
Internal And External Validity
When measuring the validity of a psychological research study, psychologists need to understand whether the results occur by mere chance rather than from the study itself, and whether the results are useful in the real world. This is measured by determining internal and external validity.
Internal validity determines that the effects observed in a study are caused by manipulating the independent variable and not by an external factor. One way that psychologists demonstrate internal validity is by having a control group in their research study, where the independent variable is not modified. If both groups show the effect, then the independent variable is not the cause, and this is a factor in demonstrating a lack of internal validity.
External validity is how well the results of a study can be generalized. If the results can only be reproduced in a lab or highly controlled study, the utility of the research falls, and this may be a factor in demonstrating a lack of external validity.
Types Of Validity
Content related validity describes how well a measure covers all aspects of the construct being measured.
Criterion related validity measures the performance of a test based on already known criteria or expected outcomes.
Face validity describes how a test appears at face value. To measure it you could ask other people who might use the test if they think it looks accurate. It can be more subjective but is still useful for detecting obvious errors.
Construct validity describes how well a measure describes the abstract concept (construct).
Convergent Validity describes how well two measures that should be related are related.
Concurrent validity describes how well a measure compares to existing measures. If a new measure assesses the same or a very similar thing as an existing one, the two should be compared. If the results differ across a sample from the same population, it’s important to find out why. Is the new measure more accurate? Or is it defective?
Predictive validity describes how well a measure predicts real world outcomes or results.
Discriminant validity sometimes called divergent validity refers to how well something does not measure with measurements of constructs it shouldn’t be related to. Establishing it helps support the claim that the test or measure is measuring the construct it’s supposed to rather than something else.
Why Test Validity Matters
The process of establishing test validity is time-consuming and, depending on the area of research, can be expensive. This is part of the scientific process that produces accurate psychological assessments, tests, and measures. The exhaustive measures to establish test validity keep the process of psychological tests, measurements, and assessments ethical and fair; they protect the credibility of the psychological community as a whole and prevent errors that could cause real-world harm.
Want To Learn More?
I included the list of sources I used while researching for this article. The majority of them are open access and do not require academic credentials or payment. I believe they are all worth reading.
Sources
Cherry, K. (2026, January 13). Validity in psychology: Definition and types. Verywell Mind. https://www.verywellmind.com/what-is-validity-2795788
Cherry, K. (2025, May 13). Validity in psychology: Definition, types, examples. Explore Psychology. https://www.explorepsychology.com/validity-psychology
Heffernan, E. (2025, November 26). Types of validity in research: Definition & examples. QuillBot. https://quillbot.com/blog/research/types-of-validity
McBride, D. M. (2024). The process of research in psychology (5th ed.). SAGE Publications.
McLeod, S. (2023, December 15). Validity in psychology research: Types & examples. Simply Psychology. https://www.simplypsychology.org/validity.html
McLeod, S. (2024, December 8). Discriminant validity (divergent validity). Simply Psychology. https://www.simplypsychology.org/discriminant-validity.html
Open Bay Path University. (n.d.). Reliability and validity. In PSY101: Introduction to psychology. https://open.baypath.edu/psy101introductiontopsychology/chapter/reliability-and-validity
OpenStax, & Lumen Learning. (n.d.). The reliability and validity of research. Pressbooks. https://pressbooks.online.ucf.edu/lumenpsychology/chapter/reading-reporting-experimental-research
The Honking Goose 