As researchers collect large amounts of data in the social sciences through household surveys, challenges may arise in how best to analyze such datasets, especially where motivating theories are unclear or conflicting. New analytical methods may be necessary to extract information from these datasets. Machine learning techniques are promising methods for identifying patterns in large datasets, but have not yet been widely used to identify important variables in social surveys with many questions. To demonstrate the potential of machine learning to analyze large social datasets, we apply machine learning techniques to the study of migration in Bangladesh. The complexity of migration decisions makes them suitable for analysis with machine learning techniques, which enable pattern identification in large datasets with many covariates. In this paper, we apply random forest methods to analyzing a large survey which captures approximately 2000 variables from approximately 1700 households in southwestern Bangladesh. Our analysis ranked the covariates in the dataset in terms of their predictive power for migration decisions. The results identified the most important covariates, but there exists a tradeoff between predictive ability and interpretability. To address this tradeoff, random forests and other machine learning algorithms may be especially useful in combination with more traditional regression methods. To develop insights into how the important variables identified by the random forest algorithm impact migration, we performed a survival analysis of household time to first migration. With this combined analysis, we found that variables related to wealth and household composition are important predictors of migration. Such multi-methods approaches may help to shed light on factors contributing to migration and non-migration.
30 July 2018 in Journal of Health and Social Behavior
This paper investigates how social support differentially benefits self-rated health among men and women hospitalized with heart disease. Using cross-sectional data about patients admitted to a university hospital, we examine the extent to which gender moderates effects for the frequency of contact with family, friends, and neighbors on health and whether these effects differ between those with new versus established diagnoses. We find that gender differentiates the effect of nonmarital family contact on health but only when heart disease is newly diagnosed. When newly diagnosed, more frequent contact with family is associated with better self-rated health for women but not men. Men and women with preexisting diagnoses benefit equally from more frequent contact with family.
9 November 2020 in RSF: The Russell Sage Foundation Journal of the Social Sciences
Thorization. In contrast, executive actions by President Donald J. Trump have boosted immigration enforcement, banned persons of particular national origins from U.S. entry, and limited noncitizens' access to asylum. Studies about the visa system and legal immigration have taken a back seat to a much larger and growing body of work on unauthorized migration. The objective of this issue of RSF: The Russell Sage Foundation Journal of the Social Sciences is to invigorate scholarly interest in legal immigration. Building on existing studies, which largely focus on wage differences among immigrants with different visas, as well as between them and U.S. natives, we aim to provide a comprehensive overview of the legal immigration system with new scholarship on the topic. Decades of backlogs
Gender and migration is a complex relationship, involving dynamic interactions between women and men, embedded in a variety of institutions (families, labor markets, and others) that all vary across different periods of historical time. Although many studies in the field of gender and migration have appeared since the late 1970s, few contemporary migration scholars centrally integrate gender into their work. In 2006, Donato and colleagues called for advancing this field of research. Now, more than a decade later, studies have incorporated various methods and approaches, but despite some momentum, most recent books and articles about migration still do not explicitly integrate gender. In this introduction, we set the stage for research and findings that bridge this gap and appear in this special issue. We preview findings from these studies, suggesting that a gender analytical framework is essential to understanding migration in the 21st century.
8 July 2019 in The Annals of the American Academy of Political and Social Science
This study considers gender differences in the health of Mexican migrants who return to Mexico from the United States, and Mexican nonmigrants. We use health data before and after migration to examine disparities in women’s and men’s childhood and adult health, comparing returned migrants and nonmigrants in Mexico. Using data on more than 14,000 household heads and their spouses interviewed between 2007 and 2016 in the Mexican Migration Project, we find evidence of only a few gendered patterns of health among migrants. Specifically, women migrants are more positively selected on height than are male migrants. We also find a stronger, positive association between migration and smoking among women: although women are less likely to smoke than men, the difference is smaller among returned migrants than among nonmigrants. In contrast, we find no evidence that the positive migrant selection on self-rated health at age 14, or negative migrant selection on emotional disorders, varies by gender, or that there is an association among migration and obesity, hypertension, diabetes, and heart disease.