Skip to main content

Currently Skimming:

Chapter 9 Contributed Session on Methods and Plans for Record Linkage
Pages 277-292

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 277...
... S Department; of Housing and Urban Development Scoft Meyer, Statistics Can adla Adam Pro bert, Robert Semenciw, and Yang Mao, HeaZih Canada Jane F
From page 279...
... unpeg "erode on Pede-I going mh~1-t~h Sh"I-PamB~ ogles = ~ ~~ ~ a_ ~ ~ ' ~ _ ~ ~' 279 ~
From page 280...
... which collects provincial court data and Me Remsed Uniform Crime Reporting Survey MICRO) which collects police data on cnnunal incidents.
From page 281...
... Specifically, ACCS charges which had a date of offense between July 1, 1993 and December 31, 1993, were loaded into an Access table. Similarly, UCR2 records from the Regina police department which had a report date in the same six months were loaded into an Access table.
From page 282...
... Results for Regina For Regina, the overall match rate based on an exact match for all five variables was 58%. This is calculated from 3105 of We 5360 charge records from We court data linking to violation records from police data.
From page 283...
... 3Close for Soundex = agreed on first letter and first digit of Soundex code. Possible Reasons for Unlinked ACCS Records Court and police records may not link for two distinct reasons.
From page 284...
... It is possible to use weights when doing exact matching, however, assigning weights In Access is difficult, and this is a major drawback. Probabilistic matching based on Me theory of Forego and Sunter (1969)
From page 285...
... , and generally, it is a component of the ubiquitous MS Office Suite. Another benefit of using Access is its speed.
From page 286...
... Conclusions The preliminary work using Access to perform the record linkage is very encouraging. This report focuses on one application, linking adult criminal court records to police records' but Access could also be used for other CCIS record linkage projects.
From page 287...
... ten0~! fir '~nave Record linkages are presently being carried out at Statistics Canada to link data for all immigrants to Canada from 1980 through 1994 to income tax data (for live follow-up)
From page 288...
... Whether or not data for both sexes can be analyzed, the 1980 immigration data are expected to yield the most useful results, as the follow-up period during which mortality could occur is longest for this group. Record Linkage T0 address these problems a record linkage to the income tax files was suggested, not necessarily to obtain tax information.
From page 289...
... As part ofthe regular income tax Boron, immigration date, emigration date and date of death all appear in addition to the regular tax information, if applicable. See Figure 1 for a diagram of the tax linkage procedure.
From page 290...
... Preliminary Results from Income Tax Linkage Found LandingNumber of 1980 YearImmigrants Tax Form 1980143,432 44,486 1981128,735 4,648 1982121,253 2,776 ... 1993255,087 222 1994222,538 152 Found 1994 Tax FoIm 67,782 62,956 60,771 118,795 86,943 Next Steps Tnitially, only the 1980 immigration-tax data (1980 immigrant files linked to 1980-1994 tax files)
From page 291...
... Conclusion T0 summarize, He immigration database offers the opportunity for new research into immigrant heals. By linking to Canadian income tax records, we could know when a landed urun~grant is no longer a resident of Canada, something that is not available in most immigrant studies.


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.