Deaths without denominators: using a matched dataset to study mortality patterns in the United States

Monica Alexander

No q79ye, SocArXiv from Center for Open Science

Abstract: To understand national trends in mortality over time, it is important to study differences by demographic, socioeconomic and geographic characteristics. One issue with studying mortality inequalities, particularly by socioeconomic status, is that there are few micro-level data sources available that link an individual's SES with their eventual age and date of death. In this paper, a new dataset for studying mortality disparities and changes over time in the United States is presented. The dataset, termed 'CenSoc', uses two large-scale datasets: the full-count 1940 Census to obtain demographic, socioeconomic and geographic information; and that is linked to the Social Security Deaths Masterfile (SSDM) to obtain mortality information. This paper also develops mortality estimation methods to better use the 'deaths without denominators' information contained in CenSoc. Bayesian hierarchical methods are presented to estimate truncated death distributions over age and cohort, allowing for prior information in mortality trends to be incorporated and estimates of life expectancy and associated uncertainty to be produced.

Date: 2018-07-23
New Economics Papers: this item is included in nep-age, nep-dem and nep-hea
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (11)

Downloads: (external link)
https://osf.io/download/5b55cd1f69e43a000fd5442b/

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:osf:socarx:q79ye

DOI: 10.31219/osf.io/q79ye

Access Statistics for this paper

More papers in SocArXiv from Center for Open Science
Bibliographic data for series maintained by OSF (contact@cos.io).