Simple strategies for improving inference with linked data: a case study of the 1850–1930 IPUMS linked representative historical samples

Abstract

New large-scale linked data are revolutionizing quantitative history and demography. This paper proposes two complementary strategies for improving inference with linked historical data: the use of validation variables to identify higher quality links and a simple, regression-based weighting procedure to increase the representativeness of custom research samples. We demonstrate the potential value of these strategies using the 1850–1930 Integrated Public Use Microdata Series Linked Representative Samples (IPUMS-LRS)—a high quality, publicly available linked historical dataset. We show that, while incorrect linking rates appear low in the IPUMS-LRS, researchers can reduce error rates further using validation variables. We also show how researchers can reweight linked samples to balance observed characteristics in the linked sample with those in a reference population using a simple regression-based procedure.     

Linking Scottish vital event records using family groups

Abstract

The reconstitution of populations through linkage of historical records is a powerful approach to generate longitudinal historical microdata resources of interest to researchers in various fields. Here we consider automated linking of the vital events recorded in the civil registers of birth, death and marriage compiled in Scotland, to bring together the various records associated with the demographic events in the life course of each individual in the population. From the histories, the genealogical structure of the population can then be built up. Rather than apply standard linkage techniques to link the individuals on the available certificates, we explore an alternative approach, inspired by the family reconstitution techniques adopted by historical demographers, in which the births of siblings are first linked to form family groups, after which intergenerational links between families can be established. We report a small-scale evaluation of this approach, using two district-level data sets from Scotland in the late nineteenth century, for which sibling links have already been created by demographers. We show that quality measures of up to 83% can be achieved on these data sets (using F-Measure, a combination of precision and recall). In the future, we intend to compare the results with a standard linkage approach and to investigate how these various methods may be used in a project which aims to link the entire Scottish population from 1856 to 1973.     

Record linkage in the Cape of Good Hope Panel*

Abstract

In this article, we describe the record linkage procedure to create a panel from Cape Colony census returns, or opgaafrolle, for 1787–1828, a dataset of 42,354 household-level observations. Based on a subset of manually linked records, we first evaluate statistical models and deterministic algorithms to best identify and match households over time. By using household-level characteristics in the linking process and near-annual data, we are able to create high-quality links for 84% of the dataset. We compare basic analyses on the linked panel dataset to the original cross-sectional data, evaluate the feasibility of the strategy when linking to supplementary sources, and discuss the scalability of our approach to the full Cape panel.     

Regional Fertility Differentials and the Effect of Migration: An Analysis of U.S. State-level Data

This paper explores, theoretically and empirically, the influence of interregional migration on regional fertility differentials. Specifically, it tests the hypothesis that regions that are closely linked through migration have, all else held constant, a lower differential in fertility than regions that are relatively isolated from one another. A model linking the fertility differential between two states to migration as well as a number of socioeconomic variables is articulated. The model is tested by means of a randomization procedure using U.S. state-level data for 1980. Results support the hypothesis that an increasing volume of interregional migration tends to lower regional fertility differentials.     

Testing Methods of Record Linkage on Swedish Censuses

Abstract.

Research benefits a great deal when different kinds of registers can be combined. Record linkage is an important tool for connecting sources to create longitudinal databases of individual data. In this article, researchers test and evaluate different methods of record linkage used when linking two censuses. By comparing the results of the census linkage with other continuous Swedish parish registers, they find that applying constructed name variables and household links considerably increases the success rate without the risk of introducing bias. Missing links are mainly related to name problems, and appear most frequently among children and when the family structure has changed between the censuses. Faulty links are very few and must be regarded as only a marginal problem for analysis. The study underlines the importance of adapting the linkage process to the special characteristics of the sources.     

Qualitative life course methodologies: critical reflections from development studies

This article reflects on two experiences of applying qualitative life course research in development studies. The first methodology centred on the elicited narratives of older people in Buenos Aires exploring their lifetime relations with their children and their current well-being. The second employed semi-structured interviews with young adults in Zambia to investigate their trajectories towards economic empowerment. In both methodologies, the roles of linked lives and of wider social, economic and political changes were central. The article contributes to critical reflection on methodological choices and trade-offs, by focusing on dilemmas that arise from a desire to address policy makers and more quantitatively-orientated researchers. It explores three themes: the challenges of making sense of disparate narratives of linked lives; the possibilities for engaging with individual subjectivities; and different strategies for situating individual experiences in dynamic social, economic and political contexts.     

The Managerial Equation and Innovation Platforms: The Case of Linköping and Berzelius Science Park

This paper explores the political and economic origins of a science park in Linköping, Sweden. It shows how different “innovation platforms” emerged to develop the medical industrial sector. An innovation platform is a foundation for growth corresponding to a given set of organizations or networks that incubate and sustain innovative teams tied to a given sector. Large firms and incubator-linked science parks represent different kinds of innovative platforms. The paper centres on the concept of the “managerial equation”, arguing that growth projects like science parks build on coalitions and networks linking innovative resources, acquired knowledge tied to a given sector and power linked to decision-making power and financial resources. Changes within these elements of the equation explain the rise and fall of innovative platforms. Failures in learning in one platform lead to the rise of another. An absence of power (such as supporting resources) can also account for platform changes. Regional development decisions do not simply reflect path dependent specializations as regions use related capacities to break into “new” sectors. Commitments to Triple Helix formations linking universities, corporations and the government reflect changes within each branch of the Helix and political decision-making creating a diversity of development pathways.     

The place of immigration in studies of geography and race

This paper argues that geographical research on immigration and geographical research on race and racism in the USA must be explicitly connected. Geographic processes such as globalization and urban development already link immigration with race and racism and suggest a need to conceptualize research agendas around immigration and race in relation to each other. Not only are racialized groups spatially connected in many neighbourhoods, cities and regions of the USA, but they are also linked through policies structured by the state at various scales and narratives produced about subordinated and racialized groups. In making this argument, I attempt to highlight work in geography, in related social sciences and in ethnic studies that demonstrates the necessity and usefulness of this approach. Geographers are uniquely positioned to illuminate how the construction of space, place and scale overlaps with the construction of racial-ethnic and immigrant identities and with racism itself. The paper argues that these and other research questions also benefit from linking race and immigration to gender, as some feminist geography and feminist studies have done. Likewise, ethnic studies offer a wealth of theoretical, methodological and empirical insight into linking immigration, race and racism in geographical work.     

ORGANIC RESOURCES AT THE IRON AGE DÜRRNBERG SALT‐MINE (HALLEIN,AUSTRIA)—LONG‐DISTANCE TRADE OR LOCAL SOURCES?*

Remarkable preservation circumstances for organic material at the Iron Age salt‐mine on the Dürrnberg Mountain offered the opportunity to analyse a large amount of wood and human faeces. One aim of the studies was to discover the origin of the important resources food and wood. Concerning the question of ‘the linking role of the Alps in past cultures’, the archaeobotanical record proves intracultural but no intercultural connections at this place in Celtic times. The preliminary results show that the Dürrnberg population used differentiated strategies to manage a continuous food and wood supply. While the wood supply was based on the management of local sources, the food supply had to be linked into a regional and long‐distance trade system.     

Spatial/temporal mismatch: a conflation protocol for Canada Census spatial files

The Canada census is one of the chief sources of demographic and socio-economic data for researchers in this country. Census variables are linked to geography files that allow researchers using geographic information systems (GIS) to view and analyze spatial data. Some of the most useful analysis, however, is based on changes in attribute values over time and space. Analysis of spatio- temporal events such as shifting migration patterns or changes in the distribution of health status permits a more dimensioned perspective than the viewing of static spatial phenomena. The analysis of spatio-temporal phenomena is limited by major changes in the spatial framework (e.g., location of road networks and other spatial entities) between national censuses. This paper addresses this limitation by (i) illustrating the extent of spatial mismatch between the 1996 and the 2001 census; (ii) examining attempts to rectify this problem in other jurisdictions and (iii) presenting a 'made-in-Canada' solution for conflation of census geometries. We believe that this solution will enhance the ability of Canadian researchers to describe and analyze socio-economic, health and demographic shifts across time and space. The research is supported by an ftp site for downloading the census geography rectification software presented in this paper.     

Flotation samples and some paleoethnobotanical implications

The size and composition of carbonized plant assemblages are integral to explanations about human use of plants. Experimental data indicate that the techniques researchers use to collect and process flotation samples can negatively affect the yield of carbonized plant remains, and thus critically alter the results of analysis. Recovery rates can be linked to the characteristics of the sediment matrix and the specific remains involved. Because the record is subject to current ideas and biases and, it, in turn, influences how researchers assign meanings, the described variations are relevant to paleoethnobotanists and archaeologists alike.     

Connecting climate variability and conflict: Implications for empirical testing

Quantitative research on climate variability and conflict is frequently criticized for being theoretically underdeveloped. In this article I discuss the most plausible suggested mechanisms connecting climate variability to conflict explicitly in reference to empirical testing. This approach could help solve the puzzle of how climate variability and conflict are related by highlighting how researchers can establish the key elements in the causal argument before moving on to testing it empirically. More specifically, I emphasize four key elements when evaluating each individual mechanism: first, who are the most relevant actors, second, what are the actors reacting toward (what type of climate variability), third, what conflict type is the most likely outcome, and fourth, what is the most appropriate temporal and spatial scale for each individual mechanism. Although empirical studies have moved toward more focus on theory and explicit tests of hypotheses derived from theoretical frameworks, an overview of how mechanisms are likely to manifest themselves and a discussion on how researchers can model them in analyses are missing in the research field. Adding technical fixes or new datasets to empirical testing does not automatically improve our understanding of the relationship between climate variability and conflict if the choices are not anchored in theoretical expectations.     

Habitat preference of extant African bovids based on astragalus morphology: operationalizing ecomorphology for palaeoenvironmental reconstruction

The habitat preferences of fauna found at palaeontological and archaeological sites can be used to investigate ancient environments and hominin habitat preferences. Here we present a discriminant function model linking astragalus morphology to four broadly defined habitat categories (open, light cover, heavy cover, and closed) using modern bovids of known ecology. Twenty-four measurements were taken on a sample of 286 astragali from 36 extant African antelope species. These measurements were used to generate ratios reflecting shape. An 11 variable discriminant function model was developed that had high classification success rates for complete astragali. Resubstitution analysis, jackknife analysis, and the classification of several “test samples” of specimens suggest that the predictive accuracy of this model is around 87%. The total classification success rates of 87% (jackknifed) or 93% (resubstitution) are considerably higher than those derived in another study of bovid astragalus ecomorphology (67%; [DeGusta, D., Vrba, E.S., 2003. A method for inferring palaeohabitats from the functional morphology of bovid astragali. J. Archaeol. Sci. 30, 1009–1022]) that used a more limited measurement scheme and a smaller sample of bovids than the present study. Different approaches to operationalizing ecomorphic analyses are considered in order to best extract accurate palaeoenvironmental information from palaeontological and archaeological datasets.     

On Neanderthal subsistence strategies and land use: A regional focus on the Rhone Valley area in southeastern France

This study of Middle Palaeolithic assemblages from the Rhone Valley, in the South-East of France, increases our understanding of Neanderthal subsistence strategies and modes of territorial organisation by comparing a wide corpus of human occupations in limited chronological and geographical frameworks. The Neanderthal occupation modes may be examined using sites located in a reduced area, linking medium-altitude territories (Massif Central and the Alpine foothills) to the Rhone corridor. Through the combined analysis of the occupation levels of ten sites, all dated to between Marine Isotopic Stage (MIS) 7 and the beginning of MIS 3, we identify three types of occupation durations: (1) type 1 as long-term residential camps, (2) type 2 as short-term regular hunting camps and (3) type 3 as brief stopover camps. We discuss this variability of habitat types according to various parameters: site age, technical behaviour, environmental conditions, and site localisation and occupation seasons. The aim is to discern the underlying motivations behind Neanderthal group mobility. One of the main features of the Rhone Valley area is the great homogeneity of behaviours reflected within the sequences. This homogeneity, linked to the variability of the site occupations, supports the hypothesis of Neanderthal groups anticipating their land use requirements, and furthermore suggests that another type of circulating model was used in this area.     

Projectile points,people, and Plains Paleoindian perambulations

Archaeologists generally agree that Paleoindian residential groups moved regularly over extremely large ranges. However, on the Great Plains, this argument depends substantially on datasets derived largely or entirely from projectile points rather than from systematic analysis of a wide range of artifacts. This paper argues that projectile points differ from most Paleoindian tools in ways that make such datasets unlikely to be reliable sources of information on range sizes. Furthermore, evidence from Paleoindian tool caches and the condition of discarded points suggest strongly that the raw material used to produce projectile points at least sometimes moved across the Plains independently of material used to make most other kinds of flaked stone tools. This, in turn, implies that not all stone used during Paleoindian times was procured by visits of whole residential groups to raw material sources, raising serious questions about the validity of widespread views of Paleoindian mobility.     

关于第二轮省志与首轮省志衔接的几个问题——从《第二轮（江苏省志）编纂方案》说起

第二轮省志必须与首轮省志衔接。一是时空范围上的衔接。时限上与前志衔接的起始资料特别是续志上限资料不能缺,地域上过去隶属地域与现行区划有从属关系的资料不应漏,规定地域范围与域外横向联系的资料应准确选用,专业上主体内容要翔实、涵盖面要广,与其他专业横向交叉资料的选用力避重叠。二是体例结构上的衔接。体裁要在继承前志的基础上有所突破和拓展,多角度、深层次、全方位地反映记述事项,篇目要保持与前志基本门类的衔接,便于类目调整后的内容衔接。三是记述内容上的衔接。承前简述用于续志起始内容的记述,旨在勾连前志、承接续志,可灵活采用覆盖式、简介式、浓缩式、追溯式、铺垫式、补充式、修正式、考注式等记述手法,加强与前志的有效衔接。四是对前志的补遗考订。补遗既可明补也可暗补,亦可明暗结合,或设置专门板块、或于行文中明确补遗内容、或将补遗内容融入承前简述,考订实质是对前志的纠错,宜采取明暗结合、分散处理办法,慎用“大集中”,以免误导读者、损及前志。     

Thinking with Montaigne: evidence, scepticism and meaning in early modern demonology

In 1612 the Bordeaux witchcraft inquisitor Pierre de Lancre (1556–1631), himself linked by marriage to Michel de Montaigne (1533–1592), revealed that the essayist and sceptic was related on his mother’s side to a leading authority on magic and superstition, the Flemish-Spanish Jesuit Martin Delrio (1551–1608). De Lancre confounded historians' expectations by using the revelation to defend Montaigne against his cousin's criticism. This article re-evaluates the relationships of De Lancre, Delrio and Montaigne in the light of recent scholarship, which casts demonology as a form of "resistance to scepticism" that conceals deep anxiety about the existence of the supernatural. It explores De Lancre’s and Delrio’s very different attitudes towards Montaigne and towards evidence and scepticism. This, in turn, reveals the different underlying preoccupations of their witchcraft treatises. It hence argues that no monocausal explanation linking scepticism to witchcraft belief is plausible.     

Frozen Film and FOSDIC Forms: Restoring the 1960 U.S. Census of Population and Housing

In this article, the authors describe a collaboration of the Minnesota Population Center (MPC), the U.S. Census Bureau, and the National Archives and Records Administration to restore the lost data from the 1960 Census. The data survived on refrigerated microfilm in a cave in Lenexa, Kansas. The MPC is now converting the data to usable form. Once the restored data are processed, the authors intend to develop three new data sources based on the 1960 census. These data will replace the most inadequate sample in the series of public-use census microdata spanning the years from 1850 to 2000, extend the chronological scope of the public census summary files, and provide a powerful new resource for the Census Bureau and its Research Data Centers.