@article{Kindermann_Chipperfield_Hansen_Rossiter_Wright_2017, title={Measuring precision for deterministic and probabilistic record linkage: IJPDS (2017) Issue 1, Vol 1:091, Proceedings of the IPDLN Conference (August 2016)}, volume={1}, url={https://ijpds.org/article/view/110}, DOI={10.23889/ijpds.v1i1.110}, abstractNote={<p><strong>ABSTRACT</strong></p> <p><strong>Objectives<br></strong>Various organisations are increasingly linking administrative, survey, and census data to enhance dimensions such as time and breadth or depth of detail. Because a unique person identifier is often not available, records belonging to two different people may be incorrectly linked. Estimating the proportion of links that are correct, called precision, is difficult because, even after clerical review, there will remain some uncertainty about whether a link is in fact correct or incorrect.</p> <p>This presentation proposes some methods for estimating precision when using either deterministic (rules-based) or probabilistic linkage. These methods are model-based and do not require clerical review. The main uses of these methods are to estimate:</p> <p>1. Precision during the linking process. This is useful to refine how linkage is carried out, such as the choice of linking variables and weight thresholds.</p> <p>2. Precision after the files are linked. This provides a useful "quality indicator" of the linked data.</p> <p><strong>Approach</strong><br>Two methods of estimating precision are described:</p> <p>1. Simulation – the linking process is simulated many times, whether it is probabilistic or deterministic. The key step being the simulation of the agreement pattern between data sets, based on underlying probabilities.</p> <p>2. An algebraic estimator – this is applicable for deterministic linking only, and provides a quicker way of estimating precision.</p> <p>Both methods are investigated using two studies: (i) synthetic data (ii) real data (death registrations linked to census data).</p> <p><strong>Results</strong><br>The estimators perform very well using both the synthetic and real data, even when assumptions about the independence of linking variables are violated. This suggests that the estimators are robust against moderate violations of these assumptions.</p> <p><strong>Conclusion</strong><br>The proposed estimators of precision are a very useful addition to the record linkage tool kit, providing methodical, faster, and cheaper alternatives to many present strategies that rely on clerical review. Estimates of precision are useful in the planning, process, and analysis of record linkage activities.</p>}, number={1}, journal={International Journal of Population Data Science}, author={Kindermann, Bindi and Chipperfield, James and Hansen, Noel and Rossiter, Peter and Wright, Jeffrey}, year={2017}, month={Apr.} }