To wish impossible things: On the ontological status of latent variables and the prospects for theory in psychology

In this commentary, we argue that Fried's article, "Lack of theory building and testing impedes progress in the factor and network literature," provides a number of insights that will be very useful for psychologists, but also that he is wishing for psychology to focus on a kind of theory that it cannot generally be expected to produce at this time. As we will explain, Fried asks too much of our models and our theories. In part, this stems from a failure to consistently heed his own warnings about the limitations of statistical models, but it also reflects an overestimation of the kind of evidence and reasoning necessary to develop and test theory. We too believe that psychological research on individual differences should pay attention to theory, but we are more optimistic than Fried about the progress that can be made through a focus on the kind of theory that psychology is actually capable of producing. In order to justify our optimism, we first develop our perspective on the nature of latent variables and then consider how individual-difference researchers should approach theory that has the potential to explain them.