The present financial and economic crisis has revealed a systemic failure of academic economics and emphasized the need to re-think how to model economic phenomena. Lawson (2009) seems concerned that critics of standard models now will fill academic journals with contributions that make the same methodological mistakes, albeit in slightly different guise.  In particular, he is rather sceptical to use of mathematical statistical models, such as the CVAR approach, as a way of learning about economic mechanisms. In this paper I discuss whether this is a relevant claim and argue that it is likely to be based on a misunderstanding of what a proper statistical analysis is and can offer.  In particular, I argue that the strong evidence of (near) unit roots and (structural) breaks in economic variables suggests that standard economic models need to be modified or changed to incorporate these strong features of the data. Furthermore, I argue that a strong empirical methodology that allows data to speak freely about economic mechanisms, such as the CVAR, would ensure that important information in the data is not over heard when needed. Adequately applied such models would provide us with an early warnings system signalling that the economy is moving seriously out of equilibrium.