Missing data is a common challenge in research when using administrative or survey data. If data missingness is not properly addressed, it can lead to invalid estimates and misleading analysis, impacting decision making.

The Office for National Statistics (ONS) asked Alma Economics to conduct a technical review of the literature on the methods that can be used to deal with missing data. Our team carried out a Rapid Evidence Assessment aimed at identifying the most prevalent causes of missing data, the main consequences, and the methods that can be applied to address these gaps for administrative and other non-survey data. Our report discusses the main benefits and drawbacks of each method, including their suitability for different types of datasets and causes of missingness.

We also developed an interactive Evidence Map, synthesising and presenting all the evidence collected. Finally, we developed a Python example code to illustrate how different methods can be applied under different scenarios of missing data.

Our research is particularly relevant for the ONS population and migration statistics transformation programme, aiming to make greater use of administrative data for more frequent and timely outputs.

➥ Read our report here.