This paper describes the procedures leading to the construction of an integrated dataset for business firms. By merging information from sources such as business registries, financial statements and intellectual property offices, we show how to assemble a panel data that is suited to investigate issues ranging from firm demographics to industrial dynamics, also encompassing the analysis of innovation activities taking place within business firms. We test the validity of the proposed procedures resorting to the virtual universe of Italian limited liability companies, hence covering more than 1 million firms operating in both manufacturing and service sectors. The main purpose of the paper is to provide a unified set of procedures to help researchers dealing with the vast amount of information available on corporate firms and of ever increasing size. Our work also contributes to ease the replicability of empirical analyses.
- Firm-level data
- Structural Business Statistics
- firm demography
- integrated database
- intellectual property