@techreport{f1c3c305590a4d7cb36c4f74575a1f35,
title = "Testing Gibrat's Legacy: A Bayesian Approach to Study the Growth of Firms",
abstract = "Gibrat's law is a referent model of corporate growth dynamics. This paper employs Bayesian panel data methods to test for Gibrat's law and its implications. Using a Pharmaceutical Industry Database (1987-1998), we find evidence against Gibrat's law on average, within or across industries. Estimated steady states differ across firms, and firm sizes and growth rates don't converge within the same industry to a common limiting distribution. There is only weak evidence of mean reversion: initial larger firms do not grow relatively slower than smaller firms. Differences in growth rates and in size steady state are persistent and firm-specific, rather than size-specific.",
keywords = "Gibrat's Law, Firm Growth, Pharmaceutical Industry, Heterogeneity, Bayesian Estimation",
author = "E. Cefis and M. Ciccarelli and L. Orsenigo",
year = "2005",
language = "English",
series = "Discussion Paper Series / Tjalling C. Koopmans Research Institute",
publisher = "UU USE Tjalling C. Koopmans Research Institute",
number = "02",
type = "WorkingPaper",
institution = "UU USE Tjalling C. Koopmans Research Institute",
}