Skip to main content

Currently Skimming:

Chapter 1 Keynote Address
Pages 1-12

The Chapter Skim interface presents what we've algorithmically identified as the most significant single chunk of text within every page in the chapter.
Select key terms on the right to highlight them within pages of the chapter.


From page 1...
... Record Linkage Techniques- 1997 Keynote Address: Record Linkage and Public Policy A Dynamic Evolution Chair: Martha Riche, Bureau of the Census Speaker: Ivan P Fellegi, Statistics Canada 1
From page 3...
... There is a single record as wed as a file of records and all records relate to some entities: persons, businesses, addresses, etc. Record linkage is We Lemon ~at, using the identifying information contained in the single record, seeks another record in the file referring to the same entity.
From page 4...
... . Second, new computer technology facile the maintenance of these files, the practically unlimited integration of additional information, end the extraction of hitherto unimaginably complex information from them (means)
From page 5...
... Our first contribution involved formalizing this Rive recognition and rigorously describing the space of record pairs consisting of all possible conlpaIisans, · Second, we provided a calculus for co~armg Be evidence conned ~ dirt record pairs about the likel~ood~at~ey refer tome same underlying unit; · Third, we deiced a linkage rule as a paring of a comparison space into the subset that we called "liked," i.e., record pairs about which He inference is Hat they indeed refer to He same underlying wig, a second subset for which the inference is Cat the record pairs refer to different underlying units, and a complementary~ird set where~che inference cannot be made without furler evidence, Fourth, as a formalization of He stoical character of He linkage rule, we identified the characteristic Type ~ and Type II errors associated with a given linkage rule: He proportion of record pairs that are falsely linked and He proportion that are incorrect ly Raked; · Fifth, we showed Hat if He space of record pair comprises is ordered according to our metric, this will result in a linkage rule Hat is oph}na1 for any pre~ecified Type ~ and Type II error levels; · Our final contribution was to provide a fiamework ~at, in retrospect, turned out to be ~ both for the design of operationally efficient record linkage systems and for He identification of useful areas for Ether research. Perhaps this was our most important contribution: facing He outstanding research Hat followed.
From page 6...
... Statistics Canada win ~mder~ke record Age activities only if acme foDow~ng canyons are satisfied: He purpose of Be linkage active is statistical/research, me products of the activity win be released Ally In accordance web He confidential provisions of He Statistics Act; ~ me,. He benefits to be derived Tom He linkage are substantial and clearly serve He public interest; · record linkage is either the Fly option to acquire the needed infonnation or, given He cost or burden implications of alternative approaches, it is the Ally feasible a$rtion; Be record linkage activity will not be used for purposes that can be detrimental to the individuals involved; He record linkage activity is judged not to jeopardize Be future conduct of St~isthcs Canada's programs; and finally · He linkage satisfies a prescribed review and approval process.
From page 7...
... If Be proposal involves more Can a scientific fishing expedition, i.e., if it is designed to explore a reasonably weD-founded scientific hypothesis, then the linkage is normally approved by He senior management of Statistics Canada, since the precedent for ministerial approval is well established in these cases. in other cases where Here is no applicable precedent the public benefit is considered carefully by Statistics Canada.
From page 8...
... proves Cat a well balanced policy, together with concrete administrative practice to give it effect, can effectively mediate between Metro competing public goods of privacy end need to lmow. The Dog That Does Not Bark: Public Administration and Public Unconcern T arge government data banks about persons have traditionally been regarded as Omening because ofthe visible Power ofthe she: to make compulsory the provision of inibr~r~ion~at it needs, to make decisions on He basis of information in its possession, and finally to enforce the decisions made on the basis of the information held.
From page 9...
... ~ believe~ere is a greet need for much increased transparency here. We need to develop explicit and publicly debatable policies about both the criteria and processes involved In approving record linkage for adminis~adve purposes - perhaps alongil~e lines of We process used by Statistics Canada, but of course suitably modified to fit Me different domains of application.
From page 10...
... But the cheap availability of computing, together with the powerfi m~hodology-based software has altered He picture. Indeed, we in Statistics Canada were able to cc~s~uct' as part of our 1991 census preparation, an excellent address list usmg client lists from the tax authority, telephone companies, hydra companies and municipal assessments.
From page 11...
... A requirement for the license would be the obligation to provide free access by people to the information held about themselves, as well as the oblivion to m,Dlement all corrections on demand. Since compliance with these regulations would improve the accuracy of information held m such data banks, registered carriers would have a competitive advantage.
From page 12...
... It is, however, a paradox that as the relative balance of power is shying to Be private sector, we are aDowing it to build up extensive person rig banks, without regulation or even assurances about the accuracy of its c~. The power that we used to be anxious to deny to the state, Rich is ~e'aLilig under Be guidance of our ele~represer~ives, we are aDowing the private sector to acquire - Ewe seen~to be doing so with a shrug of the shoulders in a democratic society it is of paramount importance Cat major public issues be decided based on wed Informed public debate.


This material may be derived from roughly machine-read images, and so is provided only to facilitate research.
More information on Chapter Skim is available.