Theory Before the Test: How to Build High-Verisimilitude Explanatory Theories in Psychological Science

Abstract

Drawing on the philosophy of psychological explanation, we suggest that psychological science, by focusing on effects, may lose sight of its primary explananda: psychological capacities. We revisit Marr's levels-of-analysis framework, which has been remarkably productive and useful for cognitive psychological explanation. We discuss ways in which Marr's framework may be extended to other areas of psychology, such as social, developmental, and evolutionary psychology, bringing new benefits to these fields. We then show how theoretical analyses can endow a theory with minimal plausibility even before contact with empirical data: We call this the theoretical cycle. Finally, we explain how our proposal may contribute to addressing critical issues in psychological science, including how to leverage effects to understand capacities better.

Keywords: computational analysis; computational-level theory; formal modeling; levels of explanation; psychological explanation; theoretical cycle; theory development.

A sorting network. Imagine a maze structured this way; each of six people, walking from left to right, enters a square on the left. Every time two people meet at any node (circle) they compare their height. The shorter of the two turns left next, and the taller turns right. At the end of the maze, people end up sorted by height. This holds regardless of which six people enter the maze and of what order they enter the maze. Hence, the maze (combined with the subcapacity of people for making pairwise comparisons) has the capacity for sorting people by height. Adapted from https://www.csunplugged.org, under a CC BY-SA 4.0 license.

Fig. 1.

The empirical cycle is familiar to most psychological scientists: The received view is that our science progresses by postulating explanatory hypotheses, empirically testing their predictions (including, but not limited to, effects), and revising and refining the hypotheses in the process. Explanatory hypotheses often remain verbal in psychological research. The first steps of (formal) theory building include making such verbal theories formally explicit. In the process of‘ formalization the verbal theory may be revised and refined. Theory building does not need to proceed with empirical testing right away. Instead, theories can be subjected to rigorous theoretical tests in what we refer to as the theoretical cycle. This theoretical cycle is aimed at endowing the (revised) theory with greater a priori plausibility (verisimilitude) before assessing the theory’s empirical adequacy in the empirical cycle.

Fig. 2.

The universe of all possible functions (indicated by the rectangle) contains infinitely many possible functions. By applying several constraints jointly (e.g., tractability, learnability, evolvability) psychological scientists can reduce the subset of candidate functions to only those plausibly describing real-world capacities.