14 October 2026
Understanding the effect of events or actions is crucial for decision-makers in the services sector and in the industry as a whole. One of the main challenges in data analyses in this context is that datasets rarely contain all the necessary information. This occurs either because analysts cannot identify all the countless factors influencing the indicators of interest or because, even if all the factors were known, some of them might not be measurable (e.g., organisational culture and leadership style). As a consequence, conclusions from quantitative analyses based on many traditional methods may be misleading and result in inappropriate decisions.
In his recent publication, “Causal Inference Without Complete Information: A Closed-Form Solution” appearing in the British Journal of Management, Dr Fernando Moreira tackles this issue by proposing simple formulas that allow practitioners and researchers to disentangle the true effect of one indicator on another from relationships driven by information not included in the datasets analysed.
The accuracy of the method’s results is supported by extensive simulations and an application to a real-world dataset, both of which indicate that the approach outperforms classical quantitative methods while avoiding many of their restrictive assumptions and requirements.
This study has the potential to initiate a new stream of research in causal inference as it looks at the problem from a novel angle and opens avenues for overcoming the limitations of existing approaches. The relative simplicity of the proposed formulas makes them accessible to a broad audience, requiring no advanced mathematical or statistical knowledge.