Firm Size and Growth Rate Variance: the Effects of Data Truncation

This paper discusses the effects of the existence of natural and/or exogenously imposed thresholds in firm size distributions, on estimations of the relation between firm size and variance in firm growth rates. We explain why the results in the literature on this relationship are not consistent. We argue that a natural threshold (0 number of employees or 0 total sales) and/or the existence of truncating thresholds in the dataset, can lead to upwardly biased estimations of the relation. We show the potential impact of the bias on simulated data, suggest a methodology to improve these estimations, and present an empirical analysis based on a comprehensive dataset of Dutch manufacturing and service firms. The only stable relation between firm size and growth rate variance is negative regardless of how we define the measure of firm growth.