Returns to Higher Education - Graduate and Discipline Premiums

Zhu, Yu; Xu, Lianhua

doi:10.2139/ssrn.4114886

Cited by 2 publications

(1 citation statement)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Evaluation of educational policies is facilitated by population wide educational attainment registers [ 20 ]. These kinds of data sets foster research as the example of the UK Longitudinal Educational Outcomes study has shown [ 36 ]. Building an educational register requires regular linking of updates on educational attainment to the register.…”

Section: Introductionmentioning

confidence: 99%

Microsimulation of an educational attainment register to predict future record linkage quality

Schnell

Weiand

2023

IJPDS

View full text Add to dashboard Cite

IntroductionPopulation wide educational attainment registers are necessary for educational planning and research. Regular linking of databases is needed to build and update such a register. Without availability of unique national identification numbers, record linkage must be based on quasi-identifiers such as name, date of birth and sex. However, the data protection principle of data minimization aims to minimize the set of identifiers in databases. ObjectivesTherefore, the German Federal Ministry of Research and Education commissioned a study to inform legislation on the minimum set of identifiers required for a national educational register. MethodsTo justify our recommendations empirically, we implemented a microsimulation of about 20 million people. The simulated register accumulates changes and errors in identifiers due to migration, regional mobility, marriage, school career and mortality, thereby allowing the study of errors on longitudinal datasets. Updated records were linked yearly to the simulated register using several linkage methods. Clear-text methods as well as privacy-preserving (PPRL) methods were compared. ResultsThe results indicate linkage bias if only the primary identifiers are available in the register. More detailed identifiers, including place of birth, are required to minimize linkage bias. The amount of information available to identify a person for matching is more critical for linkage quality than the record linkage method applied. Differences in linkage quality between the best procedures (probabilistic linkage and multiple matchkeys) are minor. ConclusionsMicrosimulation is a valuable tool for designing record linkage procedures. By modelling the processes resulting in changes or errors in quasi-identifiers, predicting data quality to be expected after the implementation of a register seems possible.

show abstract

Section: Introductionmentioning

confidence: 99%