This article suggests a modification to the conception of test validity put forward by Borsboom, Mellenberghand van Heerden (2004). According to the original definition, a test is only valid if test outcomes are causedby variation in the target attribute. According to the d-connection definition of test validity, a test is validfor measuring an attribute if (a) the attribute exists, and (b) variation in the attribute is d-connected tovariation in the measurement outcomes. In other words, a test is valid whenever test outcomes inform useither about whathashappened to the target attribute in the past, or about whatwillhappen to the targetattribute in the future. Thus, the d-connection definition expands the number of scenarios in which a test canbe considered valid. Defining test validity as d-connection between target and measured attribute situatesthe validity concept squarely within the structural causal modeling framework of Pearl (2009).
- test validity
- causal inference