This paper shows that applying simple employment-weighted OLS estimation to Davis – Haltiwanger – Schuh (1996) firm level job creation rates taking the values 2 and –2 for entering and exiting firms, respectively, provides biased and inconsistent parameter estimates. Consequently, we argue that entries and exits should be analysed separately and propose an alternative, consistent estimation procedure assuming that the size of continuing firms follows a lognormal distribution. A small-scale Monte Carlo analysis confirms the analytical results. Using a sample of Austrian firms, we demonstrate that the impact of small firms on net job creation is substantially underestimated when applying employment-weighted OLS estimation.