Virtually all quantitative microdata used by social scientists derive from samples that incorporate clustering, stratification, and weighting adjustments (Kish 1992, 1965). Such data can yield standard error estimates that differ dramatically from a simple random sample of the same size. Researchers using historical U.S. census microdata, however, usually apply methods designed for simple random samples. The resulting p-values and confidence intervals could be inaccurate and could lead to erroneous research conclusions. Because U.S. census microdata samples are among the most widely-used sources for social science and policy research, the need for reliable standard error estimation is critical. We evaluate the historical microdata samples of the IPUMS project from 1850-1930 in order to determine (1) the impact of sample design on standard error estimates and (2) how to apply modern standard error estimation software to historical census samples. We exploit a unique new data source from the 1880 census to validate our methods for standard error estimation and then we apply this approach to the 1850-1870 and 1900-1930 decennial censuses. We conclude that Taylor series estimation can be used effectively with the historical decennial census microdata samples, and should be applied in research analyses that have the potential for substantial clustering effects.

In the United States, there was a strong positive relationship between socioeconomic status and intergenerational co-residence in the nineteenth century, but an inverse relationship in the late 20th century. A 2005 study carried out by the United Nations used cross-national comparisons to suggest that a similar shift is now underway around the world. To assess whether the hypothesized change is actually taking place, however, we need historical data from a variety of countries. This paper will make use of historical census data from the IPUMS-International project in an effort to detect whether the relationship between socioeconomic status and living arrangements shifted over time. The analysis will use census data from countries in Latin America, Africa, Asia, and Europe during the last third of the twentieth century. I will assess the relationship between living arrangements and socioeconomic status using indicators such as education, occupation, and housing characteristics.

Integrated census microdata constitute a new resource for social science research and policy making. The IPUMS-International project (www.ipums.org/international) is a global initiative in cooperation with national statistical authorities world-wide to anonymize, integrate and disseminate samples of census microdata. Extracts adapted to the specific research needs of each user are distributed as ASCII textfiles along with the corresponding metadata without charge via the Internet. Researchers analyze the data using their own software and hardware. This paper offers a brief over-view of the project and invites official statistical agencies in Africa to obtain additional information about participating in the IPUMS initiative by emailing the principal author of this paper. To illustrate one possible application for evidence-based policy making with respect to the Millennium Development Goals, microdata from the 2000 census of Mexico are used to measure progress toward the attainment of universal primary education and the elimination of gender inequities in access to primary education.

Thanks to the pioneering efforts of Dr. Gustavo Cabrera and other leading demographers, Latin America contains a vast archive for census microdata, the majority of which, however, are inaccessible to researchers.Throughout his academic and scientific career, Professor Cabrera was constantly concerned with information sources. The Integrated Public Use of Microdata Series for Latin America (IPUMS-AL) has embarked on the difficult task of integrating the census microdata from this region by making intensive and extensive use of new technologies, but above all, by infusing them with the determination with which Latin American institutions and eminent demographers have sought to improve the quality and ensure the preservation of these data, which undoubtedly constitute one of Latin America's statistical treasures.The IPUMS-Latin American project has the financial basis required to incorporate these microdata into a single data base that will be used for academic research and be accessible via the Internet. The census microdata of 1960, 1970, 1990 and 2000 on Mexico have already been integrated (www.ipums.org/international) as a result of the collective work undertaken by INEGI, a founding member of the project, leading Mexican demographers, and the University of Minnesota Population Center.

In the mid-nineteenth century, about 70 percent of persons aged 65 or older resided with their adult children; by the end of the twentieth century, only about 16 percent did so. According to the consensus of scholarly opinion, the simplification of the living arrangements of the aged during the twentieth century resulted primarily from an increase in the resources of the aged, which enabled increasing numbers of elderly to afford independent living. My analysis supports a different interpretation: the evidence suggests that the decline of the multigenerational family occurred mainly because of increasing opportunities for the young and declining parental control over their children.

The Minnesota Population Center is developing three large historical census microdata series: the Integrated Public Use Microdata Series (IPUMS-USA), the International Integrated Microdata Series (IPUMS-International), and the North Atlantic Population Project (NAPP). Despite many similarities, each database presents particular challenges because of variations in source materials, organization of the projects, and institutional or legal constraints. This paper describes how the challenges we face differ across ourprojects.

...This paper improves on previous attempts to infer cohabitation from the decennial census. The 1990 and 2000 censuses included specific responses for unmarried partner in the relationship question; previous censuses classified these individuals in broader partner/roommate or partner/friend categories. Our goal is to infer as best we can which individuals in the censuses of 1960 though 1980 would have described themselves as opposite sex unmarried partners if that option had been available on the census. We do this by first developing rules to identify households that are likely contain an unmarried partner, and then by applying a regression model to refine these measures...

Census microdata are an invaluable resource for social science and policy research. Until recently National Statistical Institutes permitted little access to these data. This paper reports on users and uses of the IPUMS-International database (www.ipums.org/international). The project is a global collaboratory to anonymize, harmonize and provide access on a restricted basis to integrated microdata extracts of census samples. Custom-tailored extracts and documentation are delivered, at no charge via the Internet, but access is restricted to bona fide scientists with demonstrated research needs who agree to abide by the conditions of use license. This paper summarizes information on the users and uses of the database during the first 33 months of operation.

Thanks to cooperative undertakings with national statistical agencies world-wide and to sustained funding by the National Science Foundation and the National Institutes of Health of the United States, over the next five years the University of Minnesota Population Center is extending the IPUMS-International project to 44 countries, including at least 7 Commonwealth nations. Presently, 28 anonymized, integrated census microdata samples for 8 countries, totaling more than 122 million unit records, are available at no cost to accredited researchers on a restricted-access basis from https://www.ipums.org/international. This paper briefly summarizes the confidentiality protocols, harmonization methodology, and uses of the database over the first 33 months of operation. Commonwealth producers and users of census microdata are invited to contribute to and benefit from this global initiative.

Age at first marriage increased dramatically between 1960 and 1990, especially among blacks. The median age at first marriage among black men went from 22.5 to 28.6, and among women from 20.4 to 27.8. These increases are among the most rapid ever recoded for any historical population. Census 2000 reveals a dramatic and unexpected surprise: although median age at first marriage continued to rise for black women, it declined sharply for black men (see Figure 1). The census data indicate that black men are now marrying a year younger than black women. This paper will explore the reasons behind this unusual pattern. In particular, we will assess the effects of changing age intervals between spouses among black married couples; changing patterns of intermarriage between blacks and other racial groups; underenumeration of single black men; and changes in the income distribution of young black men.