Inaccurate age and sex data in the Census PUMS files: evidence and implications

Public Opinion Quarterly (Impact Factor: 2.25). 01/2010; DOI: 10.2307/40927730
Source: RePEc

ABSTRACT We examine the physical and mental health effects of providing care to an elderly mother on the adult child caregiver. We address the endogeneity of the selection in and out of caregiving using an instrumental variable approach, and carefully control for baseline health and work status of the adult child using fixed effects and Arellano-Bond estimation techniques. Continued caregiving over time increases depressive symptoms for married women and married men. In addition, the increase in depressive symptoms is persistent for married men. Depressive symptoms for single men and women are not affected by continued caregiving. There is a small protective effect on the likelihood (10%) of having any heart conditions among married women who continue caregiving. Robustness checks confirm that the increase in depressive symptoms and decrease in likelihood of heart conditions can be directly attributable to caregiving behavior, and not due to a direct effect of the death of the mother. The initial onset of caregiving, by contrast, has no immediate effects on physical or mental health for any subgroup of caregivers.

  • [Show abstract] [Hide abstract]
    ABSTRACT: Many statistical agencies disseminate samples of census microdata, that is, data on individual records, to the public. Before releasing the microdata, agencies typically alter identifying or sensitive values to protect data subjects' confidentiality, for example by coarsening, perturbing, or swapping data. These standard disclosure limitation techniques distort relationships and distributional features in the original data, especially when applied with high intensity. Furthermore, it can be difficult for analysts of the masked public use data to adjust inferences for the effects of the disclosure limitation. Motivated by these shortcomings, we propose an approach to census microdata dissemination called sampling with synthesis. The basic idea is to replace the identifying or sensitive values in the census with multiple imputations, and release samples from these multiply-imputed populations. We demonstrate that sampling with synthesis can improve the quality of public use data relative to sampling followed by standard statistical disclosure limitation; simulation results showing this are available online as supplemental material. We derive methods for analyzing the multiple datasets generated by sampling with synthesis. We present algorithms for selecting which census values to synthesize based on considerations of disclosure risk and data utility. We illustrate sampling with synthesis on a population constructed with data from the U.S. Current Population Survey.
    Journal of the American Statistical Association 12/2010; 105(492):1347-1357. DOI:10.1198/jasa.2010.ap09480 · 2.11 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In a recent paper in the Journal of Human Resources, Dynarski (2008) used data from the 1 percent 2000 Census Public Use Microdata Sample (PUMS) files to demonstrate that merit scholarship programs in Georgia and Arkansas increased the stock of college-educated individuals in those states. This paper replicates the results in Dynarski (2008) but we also find important differences in the results between the 1 percent and 5 percent PUMS, especially for women. We also demonstrate that the author’s use of clustered standard errors, given the small number of clusters and only two policy changes, severely understates confidence intervals.
    Journal of Human Resources 02/2011; 47(1). DOI:10.2139/ssrn.1788973
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The impending retirement of the baby boom cohort represents the first time in the history of the United States that such a large and well-educated group of workers will exit the labor force. This could imply skill shortages in the U.S. economy. We develop near-term labor force projections of the educational demands on the workforce and the supply of workers by education to assess the potential for skill imbalances to emerge. Based on our formal projections, we see little likelihood of skill shortages emerging by the end of this decade. More tentatively, though, skill shortages are more likely as all of the baby boomers retire in later years, and skill shortages are more likely in the near-term in states with large and growing immigrant populations.Institutional subscribers to the NBER working paper series, and residents of developing countries may download this paper without additional charge at
    Economics of Education Review 07/2011; 32. DOI:10.1016/j.econedurev.2012.09.004 · 1.07 Impact Factor


Available from