Quantify missing observations in Crunchbase relative to alternative databases

Quantify the number of Crunchbase entries missing relative to alternative data sources such as S&P Capital IQ for the cybersecurity sector dataset used in this study (2010–2022), in order to assess coverage completeness and potential selection bias in the analyses.

Background

The authors discuss limitations stemming from incomplete coverage in Crunchbase, noting that some observations may be missing and that larger funding rounds are more likely to be reported, potentially inducing selection bias.

They acknowledge that Crunchbase may miss entries present in other databases (e.g., S&P Capital IQ) and explicitly state that the number of missing observations still needs to be quantified, highlighting an unresolved empirical task necessary for bias assessment.

References

We however still need to quantify the number of missing observations.

— Measuring the performance of investments in information security startups: An empirical analysis by cybersecurity sectors using Crunchbase data (2402.04765 - Maréchal et al., 7 Feb 2024) in Section 5, Conclusion (footnote)