Jonas Helgertz, Joseph Price, Jacob Wellington, Kelly J Thompson, Steven Ruggles, Catherine A Fitch
{"title":"A New Strategy for Linking U.S. Historical Censuses: A Case Study for the IPUMS Multigenerational Longitudinal Panel.","authors":"Jonas Helgertz, Joseph Price, Jacob Wellington, Kelly J Thompson, Steven Ruggles, Catherine A Fitch","doi":"10.1080/01615440.2021.1985027","DOIUrl":null,"url":null,"abstract":"<p><p>This paper presents a probabilistic method of record linkage, developed using the U.S. full count censuses of 1900 and 1910 but applicable to many sources of digitized historical records. The method links records using a two-step approach, first establishing high confidence matches among men by exploiting a comprehensive set of individual and contextual characteristics. The method then proceeds to link both men and women by leveraging links between households established in the first step. While only the first stage links can be directly comparable to other popular methods in research on the U.S., our method yields both considerably higher linkage rates and greater accuracy while only performing negligibly worse than other algorithms in resembling the target population.</p>","PeriodicalId":45535,"journal":{"name":"Historical Methods","volume":"55 1","pages":"12-29"},"PeriodicalIF":1.6000,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9281997/pdf/nihms-1803562.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Historical Methods","FirstCategoryId":"98","ListUrlMain":"https://doi.org/10.1080/01615440.2021.1985027","RegionNum":2,"RegionCategory":"历史学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2021/11/11 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"HISTORY","Score":null,"Total":0}
引用次数: 0
Abstract
This paper presents a probabilistic method of record linkage, developed using the U.S. full count censuses of 1900 and 1910 but applicable to many sources of digitized historical records. The method links records using a two-step approach, first establishing high confidence matches among men by exploiting a comprehensive set of individual and contextual characteristics. The method then proceeds to link both men and women by leveraging links between households established in the first step. While only the first stage links can be directly comparable to other popular methods in research on the U.S., our method yields both considerably higher linkage rates and greater accuracy while only performing negligibly worse than other algorithms in resembling the target population.
期刊介绍:
Historical Methodsreaches an international audience of social scientists concerned with historical problems. It explores interdisciplinary approaches to new data sources, new approaches to older questions and material, and practical discussions of computer and statistical methodology, data collection, and sampling procedures. The journal includes the following features: “Evidence Matters” emphasizes how to find, decipher, and analyze evidence whether or not that evidence is meant to be quantified. “Database Developments” announces major new public databases or large alterations in older ones, discusses innovative ways to organize them, and explains new ways of categorizing information.