Failure of economic models to anticipate the global financial crisis illustrates the need for modeling to better capture complex real-world dynamics. Conventional models—in which economic variables evolve toward equilibria or fluctuate about equilibria in response to exogenous random shocks—are ill-equipped to portray complex real-world dynamics in which economic variables may cycle aperiodically along low-dimensional ‘strange attractors’. We present a method developed in the physics literature—‘phase space reconstruction’—that reconstructs strange attractors present in real-world dynamical systems using time series data on a single variable. Phase space reconstruction provides pictures of real-world dynamics that can guide model specification