EVALUATING THE QUALITY OF ANONYMOUS RECORD LINKAGE USING DETERMINISTIC PROCEDURES WITH THE NEW-YORK-STATE AIDS REGISTRY AND A HOSPITAL DISCHARGE FILE

Linkage of same-person records across multiple databases relies on hig h-quality, uniformly available identifying information. These data qua lity issues become increasingly important when personal names are not available for record linkage. Using deterministic decision criteria, w e linked records from two population-based files in the absence of per sonal names. The sensitivity of anonymous record linkage procedures ra nged from 32 to 85 per cent for the two years studied, and the positiv e predictive value (PPV) ranged from 14 to 99 per cent. Decreasing sen sitivity and PPV were primarily attributed to (1) errors in computeriz ed identifying information and (2) the deterministic decision criteria specified for record linkage. An evaluation of the contribution of pe rsonal names to the quality of record linkage found no measurable impa ct.