Abstract
Using the approach suggested by Gabaix (Citation2011), this article demonstrates that idiosyncratic shocks in the largest firms are important for an understanding of aggregate volatility in German manufacturing industries.
JEL Classification:
Acknowledgments
All computations for this study were done inside the research data centre of the Statistical Office of Berlin-Brandenburg. The firm-level data used are confidential but not exclusive; see Zühlke et al. (Citation2004) for a description of how to access the data. To facilitate replication, the Stata do-file is available from the author on request.
Notes
1 Gabaix (Citation2009) is a comprehensive survey of power laws and applications in economics and finance.
2 The power law exponent β and its SE are estimated by the method suggested in Gabaix and Ibragimov (Citation2011), see text.
3 Note that the granular residuals lagged 2 and 3 years are very highly positively correlated in the sample of industries without industries 16 and 23 (r = 0.904) which leads to insignificant coefficients when two lags are included in the empirical model.