Sociodemographic differences in linkage error: an examination of four large-scale datasets

Abstract

BackgroundRecord linkage is an important tool for epidemiologists and health planners. Record linkage studies will generally contain some level of residual record linkage error, where individual records are either incorrectly marked as belonging to the same individual, or incorrectly marked as belonging to separate individuals. A key question is whether errors in linkage quality are distributed evenly throughout the population, or whether certain subgroups will exhibit higher rates of error. Previous investigations of this issue have typically compared linked and un-linked records, which can conflate bias caused by record linkage error, with bias caused by missing records (data capture errors).MethodsFour large administrative datasets were individually de-duplicated, with results compared to an available ‘gold-standard’ benchmark, allowing us to avoid methodological issues with comparing linked and un-linked records. Results were compared by gender, age, geographic remoteness (major cities, regional or remote) and socioeconomic status.ResultsResults varied between datasets, and by sociodemographic characteristic. The most consistent findings were worse linkage quality for younger individuals (seen in all four datasets) and worse linkage quality for those living in remote areas (seen in three of four datasets). The linkage quality within sociodemographic categories varied between datasets, with the associations with linkage error reversed across different datasets due to quirks of the specific data collection mechanisms and data sharing practices.ConclusionsThese results suggest caution should be taken both when linking younger individuals and those in remote areas, and when analysing linked data from these subgroups. Further research is required to determine the ramifications of worse linkage quality in these subpopulations on research outcomes.Electronic supplementary materialThe online version of this article (10.1186/s12913-018-3495-x) contains supplementary material, which is available to authorized users.

Research using population-based administration data integrated with longitudinal data in child protection settings: A systematic review

“…If there are linkage errors, analysts can determine methods or procedures to correct for this before conducting any analysis, while acknowledging this may not always be possible [ 7 ]. Analysts could identify linkage errors by analysing differences or similarities between linked and unlinked data [ 112 ], though this method may introduce additional bias caused by missing records [ 10 ]. A simulation exercise developed by Parrish, Shanahan [ 55 ] enables post-estimation of linkage errors.…”

“…The poor or lack of transparency in reporting data linkage processes, such as reports on linkage errors, may under or overestimate the quality of studies reported, particularly among the hard to reach populations as exemplified in these studies. The more vulnerable or hard to reach populations are often missed or miss matches, resulting in reduced sample size and loss of statistical power [ 10 , 129 ].…”

“…The linked data enables researchers to study risk and protective factors and to examine outcomes from various databases brought together [5,6]. The trend of using administrative data for research purposes has increased exponentially [7][8][9][10][11][12][13]. To date, there has not been a systematic review that has focussed on methods of analysis of integrated population-based administrative data with longitudinal data in child protection settings.…”

Incremental clustering techniques for multi-party Privacy-Preserving Record Linkage

“…While data errors in real data are possible, the degree of corruption would be probably relatively low. According to the real NSWE and NCVRT datasets, the quality of data is very high with less than 1% linkage errors when a probabilistic two-database matching technique is applied on the unencoded NSWE dataset [52] and around 10% error in the NCVRT dataset. We have tested relatively pessimistic scenarios by synthetically including 20% and 40% corruption to the matching records in NCVR datasets.…”

Using ‘Big Data’ to explore unanswered questions in ovarian cancer epidemiology

“…They can be particularly useful for studying populations which are particularly hard to access with (that is, difficult to recruit into) traditional research studies. differs by socioeconomic characteristics, and was greater for younger individuals and those in rural areas (259). However, studies that take steps to minimise the effect of these limitations can provide useful, policy-relevant findings.…”