Longitudinal business data construction and quality: two different approaches

Reducing the response burden and widening available statistical information necessitate new approaches in the National Statistical Institutes production process. Our article focuses on longitudinal data needs. Two approaches for building business longitudinal data in a context of cross-section surveys and administrative sources information are considered. The article describes construction approaches and evaluates the quality of two data bases obtained through multisources integration. The computed databases aim to represent the target population of Italian firms with 20 persons employed and over. The similarity of the distribution of the main economic variables between the target population and the computed databases is considered a basic criterion in evaluating the quality of the created databases. To this end, rank correlation, and the Fligner–Policello test are applied. In addition, representativeness R indicators are computed. No differences are found between distributions.