Breaking the Waves: A Poisson Regression Approach to Schumpeterian Clustering of Basic Innovations

The Schumpeterian theory of long waves has given rise to an intense debate on the existenceof clusters of basic innovations. Silverberg and Lehnert have criticized the empirical part ofthis literature on several methodological accounts. In this paper, we propose the methodologyof Poisson regression as a logical way to incorporate this criticism. We construct a new timeseries for basic innovations (based on previously used time series), and use this to test thehypothesis that basic innovations cluster in time. We define the concept of clustering invarious precise ways before undertaking the statistical tests. The evidence we find onlysupports the �weakest� of our clustering hypotheses, i.e., that the data display overdispersion.We thus conclude that the authors who have argued that a long wave in economic life isdriven by clusters of basic innovations have stretched the statistical evidence too far.