Section 1-5 RECORD LINKAGE ALGORITHMS & DUPLICATE GROUPS

In this section we look first at transformations involving the elements of the lineage-linked model, like we did for the family group model in the last section. Then we will look at the various ways in which information on one family group sheet duplicates information on another. This means that the individuals identified by the information are duplicates. Moving between the family group model and the lineage-linked model will require an additional set of transformations. We outline processes that apply four algorithms. The different record linkage algorithms are ways of making records out of the information used to identify individuals and comparing the resulting records with each other to detect duplicates.

1-5.1Entity class transformations of the lineage-linked model and engine.
1-5.2Algorithm I or P* linkage.
1-5.3Algorithm II or O* linkage.
1-5.4Algorithm III or O(P) linkage.
1-5.5Algorithm IV or P(O) linkage.
1-5.6An additional use of algorithm IV.
1-5.7Possible structure for individual duplicate groups.
1-5.8Possible structure of sibship duplicates.