Score contribution per author:
α: calibrated so average coauthorship-adjusted count equals average raw count
We propose a novel methodology for computing variations of aggregate productivity and its decomposition into changes of individual firms’ productivities and of industry composition. Industry productivity should be measured in principle on industry total inputs and outputs but it is believed that this measure does not allow for such decomposition. Thus, weighted averages of individual productivities are used which introduce serious biases especially when industries are heterogeneous. We propose a geometric approach where aggregate productivity can be measured directly on industry data, but nevertheless its variations can be decomposed into between and within effects plus a heterogeneity effect.