Playing with matches: An assessment of accuracy in linked historical data

This article evaluates linkage quality achieved by various record linkage techniques used in historical demography. The author creates benchmark, or truth, data by linking the 2005 Current Population Survey Annual Social and Economic Supplement to the Social Security Administration's numeric identification system by social security number. By comparing simulated linkages to the benchmark data, she examines the value added (in terms of number and quality of links) from incorporating text-string comparators, adjusting age, and using a probabilistic matching algorithm. She finds that text-string comparators and probabilistic approaches are useful for increasing the linkage rate, but use of text-string comparators may decrease accuracy in some cases. Overall, probabilistic matching offers the best balance between linkage rates and accuracy.     

The Mormon Historical Demography Project

Abstract

This article describes the background and reconstruction of the Belgian 1961 census sample file. Recently, a complete codebook for the sample file has been drawn up, and the representativeness of the sample has been evaluated as accurate, except for the loss of cases that occurred for three Belgian subregions. With the addition of the 1961 census sample, cross-sectional microdata from the five successive population censuses since that year, covering a broad range of topics, are now available to the research community. The reconstruction of the 1961 census sample was part of the activities of the HISSTAT project, which is currently being run by a consortium of research institutions in Belgium to bring together cross-sectional aggregated data since 1800, aggregated longitudinal data since 1880, and cross-sectional microdata since 1961, all covering the entire country.     

Age heaping patterns in Mosaic data

This paper analyzes the extent and nature of age-misreporting in the Mosaic data, currently one of the largest historical census microdata infrastructures for continental Europe. We use demographic measures known as the age heaping indexes to explore regional, periodic and sex-specific patterns of age misreporting across 115 Mosaic regional datafiles, from Catalonia to Moscow, during Europe's demographic ancien régime and thereafter. The paper's second significant contribution is the comparison of Mosaic-based results to those derived from two other big census data projects—IPUMS and NAPP. Beyond this exploratory data analysis, we also investigate possible sources of variation in age heaping across Mosaic data by examining how it relates to variability in socioeconomic, institutional, and environmental conditions. Overall, our systematic inquiry into quality of age reporting in Mosaic consolidates the project's potentially transformative role in comparative historical family demography and suggests some avenues for future research.     

New light on Roman census papyri through semi-automated record linkage

ABSTRACT

The census documents from Roman Egypt form the best documentary source of demographic information for the Roman Empire. Earlier collections (Bagnall and Frier 2006 Bagnall, R. S., and B. W. Frier. 2006. The demography of Roman Egypt. 2nd ed. Cambridge: Cambridge University Press. [Google Scholar]; Bagnall, Frier, and Rutherford 1997 Bagnall, R. S., B. W. Frier, and I. C. Rutherford. 1997. The census register P. Oxy. 984: The reverse of Pindar's Paeans. Papyrologica Bruxellensia, Vol. 29. Brussels: Fondation égyptologique Reine Elisabeth. [Google Scholar]) have shown that some individuals and households appear more than once within this body of evidence. This article demonstrates how semi-automated record linkage provides an efficient and systematic way of producing linkages between early historical documentary sources that are fragmentary. The process yielded more linkages with generally high probability values than previously employed linkage-by-hand methods. As the added examples show, semi-automated record linkage also proved to be a useful method to fill gaps in papyri by transferring information from one record to the other. As such, it provides new opportunities for papyrologists and epigraphers working with fragmented materials pertaining to the ancient Greco-Roman world.     

Linking the 1940 U.S. Census with modern data

Abstract

The U.S. Census Bureau has created a set of linkable census, survey, and administrative records that provides longitudinal data on the American population across the past eight decades. While these files include modern decennial censuses, Census Bureau surveys, and administrative records files from other federal agencies, the long time span is only possible with the addition of the complete count 1940 Census microdata. In this paper, we discuss the development of this linked data infrastructure and provide an overview of the record linkage techniques used. We primarily focus on the techniques used to produce a beta version of a linkable 1940 Census microdata file and discuss the potential to further document and extend the infrastructure.     

How Many Household Formation Systems Were There in Historic Europe? A View Across 256 Regions Using Partitioning Clustering Methods

Abstract

This paper reconsiders one of historical demography’s most pertinent research problems: the fiddly concept of historical household formation systems. Using a massive repository of historical census micro-data from the North Atlantic Population Project and the Mosaic project, the four markers of Hajnal’s household formation rules were operationalized for 256 regional rural populations from Catalonia in the west to central Siberia in the east, between 1700 and 1926. We then analyze these data using the Partitioning Around Medoids algorithm in order to empirically derive the “natural groups” based on the similarity and the dissimilarity of their household formation traits. Although regional differences between European household formation systems are readily identifiable, the two statistically most valid clustering solutions (k?=?2; k?=?4) provide a more complex picture of household formation regimes than Hajnal and his followers have been able to compile. Our finding that when regional populations cluster on similar household formation characteristics, they often come from both sides of Hajnal’s “imaginary line,” calls into question strict bipolar divisions of the continent. By and large, we show that the long-lived idea of two household formation systems in preindustrial Europe obscures considerable variability in historical family behavior, and therefore needs to be amended.