A psychological test is something that calls for an individual to present a certain behavior that can be used in the measurement of personal characteristic or trait or in the anticipation of outcome (Lovler, Miller & McIntire, 2010, p. 6).
Validity helps to know whether a test measures what it’s meant to measure. Making the test real to life is a way of increasing validity. Reliability is about how far the result can be depended on.
Reliability and validity are some of the crucial issues that are involved in conducting psychological testing. Validity is a very fundamental concept in both measurement and psychology. There is a great relationship between reliability and validity.
Unless the test is reliable, trying to define its validity will be pointless. Theoretically, the correlation of a test with another variable should not be higher as compared to its correlation with itself.
“The maximum validity coefficient between two variables is equal to the square root of the product of their reliabilities” (Kaplan & Saccuzzo, 2008, p. 154).
Given that validity coefficients are not required to be extra high, there may be lack of proper correlation between two scores for two traits if there is unreliability for each trait’s score. At times, it is difficult to show that a reliable test is meaningful.
This means that there can be reliability without validity. On the other hand, being able to ascertain that a reliable test is valid is not logically possible. Different types of evidence are used to establish the validity of a test.
They include content validity evidence, predictive validity evidence, construct validity evidence, concurrent validity evidence, convergent evidence and discriminant evidence (Kaplan & Saccuzzo, 2008, p.154-155).
References
Kaplan, R.M. & Saccuzzo, D.P., (2008). Psychological Testing: Principles, Applications and Issues. Belmont, U.S: Wadsworth Cengage Learning. Retrieved
Lovler, Miller & McIntire, (2010). Foundations of Psychological Testing: A Practical Approach. California: SAGE. Retrieved