Distinguishing Individual Linkages of Personal Records from Family Linkages

Abstract

Errors occur in the automated linkage of medical and other records into personal histories, when household and family identifiers get wrongly treated in the same way as the strictly personal identifiers. This is because overwhelming evidence that two records refer to the same household or family, does not mean they necessarily represent the same person. Current practice in probabilistic record linkage fails to make this distinction, and combines indiscriminately the calculated odds from the mix of identifiers pertaining to all three sorts of entity. A tactic is described that avoids the resulting problem of mistaken personal identity. It does so by first converting composite odds from comparisons of household and family particulars, to a magnitude that contributes correctly to the overall evidence in favour of a strictly personal linkage.

Key-Words

Record Linkage - Probabilistic Linkage - Patient Histories - Personal Record Updating - File Maintenance

• REFERENCES

• 1 Smith ME. Record Linkage of Hospital Admission-Separation Records (M. Sc. Thesis). Kingston, Ontario: Queen’s University; 1972
• 2 Smith ME, Newcombe HB. Methods for computer linkage of hospital admission-separation records into cumulative health histories. Meth Inform Med 1975; 14: 118-25.
• 3 Lalonde P. Deriving weights using non-links. In: Carpenter M, Fair ME. eds. Proceedings of the Record Linkage Sessions and Workshop, Canadian Epidemiology Research Conference. Ottawa, Ontario: Statistics Canada; 1989: 149-57.
• 4 Newcombe HB, Kennedy JM, Axford SJ, James AP. Automatic linkage of vital records. Science 1959; 130: 954-9.
• 5 Newcombe HB, Kennedy JM. Record linkage: Making maximum use of the discriminating power of identifying information. Comm ACM 1962; 05: 563-6.
• 6 Fellegi IP, Sunter AB. A theory of record linkage. J Amer Statis Ass 1969; 64: 1183-210.
• 7 Newcombe HB. Handbook of Record Linkage: Methods for Health and Statistical Studies, Administration and Business. Oxford: Oxford University Press; 1988
• 8 Hill T. GRLS-V2, Release 22 May 1991. (Available from Ted Hill, General Systems, R. H. Coats Building, 14-0, Statistics Canada, Ottawa Ontario K1A 0T6, Canada).
• 9 Chakraborty R, Kidd KK. The utility of DNA typing in forensic work. Science 1991; 254: 1735-9.
• 10 Lewontin RC, Hartl DL. Population genetics in forensic DNA typing. Science 1991; 254: 1745-50.
• 11 Roberts L. Fight erupts over DNA fingerprinting. Science 1991; 254: 1721-3.
• 12 Jaro MA. Advances in record-linkage methodology as applied to matching the 1985 census of Tampa, Florida. J Amer Statis Ass 1989; 84: 414-20.
• 13 Scheuren F, Winkler WE. Regression analysis of data files that are computer matched. Survey Methodology 1993; 19: 39-58.
• 14 Winkler WE. Methods of adjusting for lack of independence in an application of the Fellegi-Sunter model of record linkage. Survey Methodol 1989; 15: 101-17.
• 15 Winkler WE. String comparator metrics and enhanced decision rules in the Fellegi-Sunter model of record linkage. In: Proceedings of the Section on Suivey Research Methods J Amer Statist Ass 1990; 354-9.
• 16 Winkler WE. Empirical comparisons of record linkage decision rules. Statistical Research Division Technical Report, U.S. Bureau of the Census. Washington DC: 20233.
• 17 Howe GR, Lindsay J. A generalized iterative record linkage computer system for use in medical follow-up studies. Comput Biomed Res 1981; 14: 327-40.
• 18 Fair ME, Lalonde P, Newcombe HB. Application of exact ODDS for partial agreement of names in record linkage. Comput Biomed Res 1991; 24: 58-71.
• 19 Newcombe HB, Fair ME, Lalonde P. Discriminating powers of partial agreements of names for linking personal records. Part I: The logical basis, and Part II: The empirical test. Meth Inform Med. 1989. 28 86-91. and 92-6.
• 20 Newcombe HB, Fair ME, Lalonde P. The use of names for linking personal records. J Amer Statist Ass 1992; 87: 1193-208.
• 21 Newcombe HB. Limitations of the Simple Agree/Disagree Comparisons. (Distributed as a handout at the Workshop on Record Linkage Methodology. 15 November 1991. Ottawa, Ontario: Statistics Canada);
• 22 Belin TR. Using Mixture Models to Calibrate Error Rates in Record-Linkage Procedures, with Application to Computer Matching for Census Undercount (Ph. D. Thesis). Boston, Mass: Harvard University; 1991