Union Army Veterans, All Grown Up

Military service is a highly social—and potentially socializing—experience. However, the long-term social effect of military service is a little-studied topic, and some have dismissed any direct impact of service on civic participation. Using data from a large, national survey, our estimates show, in contrast, that the likelihood and intensity of group participation is higher among veterans than other men and that combat veterans have the highest level of participation. Mettler argued that education funded through the GI Bill gave veterans both resources (“civic capacity”) and a desire to reciprocate to society (“civic predisposition”) for the generous benefits they received, but she did not allow for the possibility that service itself could also increase both civic capacity and predisposition. Furthermore, our estimates confirm that education is strongly associated with higher civic participation and that the association between military service and participation is largely independent of education.

show abstract

“… 5. See Costa et al (2017) and Hess (2017) for introductions to the Early Indicators data set. …”

mentioning

confidence: 99%

Military Service, Combat Experience, and Civic Participation

Wilson

Ruger²

2020

Armed Forces & Society

View full text Add to dashboard Cite

show abstract

“…Names may vary over time, either because Census enumerators misspelled names, the individual reported incorrectly, or the individual changed their name (perhaps using a middle name or nickname in place of the given name). For example, Goeken et al (2017) document that in two enumerations of St. Louis in the 1880 Census, nearly 46 percent of first names are not exact matches, and the Early Indicators project notes that 11.5 percent of individuals in the Oldest Old sample have a shorter first name in pension records than in the original Civil War enlistment records (Costa et al 2017).…”

Section: Current Approaches To Linking Historical Datamentioning

confidence: 99%

“…the LIFE-M sample of birth certificates linked to the 1940 Census (Bailey 2018) and a genealogically linked sample of Union Army veterans from the Early Indicators Project (Costa et al 2017).…”

Section: A Hand-linked and Synthetic Datamentioning

confidence: 99%

“…Our second sample is the Oldest Old sample of Union Army veterans from the Early Indicators Project. Costa et al (2017) created this sample of 2,076 individuals at least 95 years old linked to the 1900 complete-count U.S. Census using genealogical methods and a rich set of supplementary information.…”

Section: A Hand-linked and Synthetic Datamentioning

confidence: 99%

“…information, allowing us to be fully transparent about our samples and assumptions in assessing algorithm performance. Our samples include the Longitudinal Intergenerational Family Electronic Micro-database's (LIFE-M) sample of birth certificates linked to the 1940 Census (Bailey 2018) as well as a sample of Union Army veterans from the Early Indicators Project genealogically linked to the 1900 Census (Costa et al 2017). These data were linked by hand using multiple levels of review by highly trained individuals and, because they were created without knowledge of the machine links, do not preference one automated method over another.…”

mentioning

confidence: 99%

See 2 more Smart Citations

How Well Do Automated Linking Methods Perform? Lessons from US Historical Data

Bailey

Cole

Henderson

et al. 2020

Journal of Economic Literature

106

View full text Add to dashboard Cite

This paper reviews the literature in historical record linkage in the United States and examines the performance of widely used record-linking algorithms and common variations in their assumptions. We use two high-quality, hand-linked data sets and one synthetic ground truth to examine the direct effects of linking algorithms on data quality. We find that (i) no algorithm (including hand linking) consistently produces representative samples; (ii) 15 to 37 percent of links chosen by widely used algorithms are classified as errors by trained human reviewers; and (iii) false links are systematically related to baseline sample characteristics, showing that some algorithms may introduce systematic measurement error into analyses. A case study shows that the combined effects of (i)–(iii) attenuate estimates of the intergenerational income elasticity by up to 29 percent, and common variations in algorithm assumptions result in greater attenuation. As current practice moves to automate linking and increase link rates, these results highlight the important potential consequences of linking errors on inferences with linked data. We conclude with constructive suggestions for reducing linking errors and directions for future research. (JEL C45, C81, J62, N31, N32)

show abstract

Automated Linking of Historical Data

Abramitzky

Boustan

Eriksson

et al. 2021

Journal of Economic Literature

113

View full text Add to dashboard Cite

The recent digitization of complete count census data is an extraordinary opportunity for social scientists to create large longitudinal datasets by linking individuals from one census to another or from other sources to the census. We evaluate different automated methods for record linkage, performing a series of comparisons across methods and against hand linking. We have three main findings that lead us to conclude that automated methods perform well. First, a number of automated methods generate very low (less than 5 percent) false positive rates. The automated methods trace out a frontier illustrating the trade-off between the false positive rate and the (true) match rate. Relative to more conservative automated algorithms, humans tend to link more observations but at a cost of higher rates of false positives. Second, when human linkers and algorithms use the same linking variables, there is relatively little disagreement between them. Third, across a number of plausible analyses, coefficient estimates and parameters of interest are very similar when using linked samples based on each of the different automated methods. We provide code and Stata commands to implement the various automated methods. (JEL C81, C83, N01, N31, N32)

show abstract

Union Army Veterans, All Grown Up

Cited by 5 publications

References 33 publications

Military Service, Combat Experience, and Civic Participation

Military Service, Combat Experience, and Civic Participation

How Well Do Automated Linking Methods Perform? Lessons from US Historical Data

Automated Linking of Historical Data

Contact Info

Product

Resources

About