Navigation

You are here: Home › Causal Inference

Tag Archives | Causal Inference

The Causal Impact of Segregation on a Disparity: A Gap-Closing Approach

By on December 6, 2025 in Articles

Ian Lundberg

Sociological Science December 9, 2025
10.15195/v12.a35

Abstract

PDF (650 views)
0 Citation


Segregation—whether across schools, neighborhoods, or occupations—is regularly invoked as a cause of social and economic disparities. However, segregation is a complicated causal treatment: what do we mean when we appeal to a world in which segregation does not exist? One could take societal contexts as the unit of analysis and compare across societies with differing levels of segregation. In practice, it is more common for studies of segregation to take persons or households as the unit of analysis within a single societal context, focusing on what would happen if particular individuals were counterfactually assigned to social positions in a more equitable way. Taking this latter framework, this article shows how to study segregation as a cause. The first step is to theorize a counterfactual assignment rule: what would it mean to assign people to social positions equitably? The second step is to identify the causal effect of those social positions and simulate counterfactual outcomes. The third step is to interpret results as the impact of a unit-level (rather than society-level) intervention. A running example and empirical analysis illustrates the approach by studying the causal effect of occupational segregation on a racial health gap.
Creative Commons LicenseThis work is licensed under a Creative Commons Attribution 4.0 International License.

Ian Lundberg: Department of Sociology, UCLA.
E-mail: ianlundberg.org, ianlundberg@ucla.edu.

Acknowledgments: For helpful discussions and feedback relevant to this project, I thank Brandon Stewart, Matthew Salganik, Dalton Conley, Sara McLanahan, Rebecca Johnson, Gillian Slee, and participants in presentations at the Princeton Department of Sociology, the Cornell Center for the Study of Inequality, and the UCSF Department of Social and Behavioral Sciences, as well as the editor and anonymous reviewers. The author benefited from facilities and resources provided by the California Center for Population Research at UCLA (CCPR), which receives core support (P2C-HD041022) from the Eunice Kennedy Shriver National Institute of Child Health and Human Development (NICHD). The content is solely the responsibility of the authors and does not necessarily represent the official views of the Eunice Kennedy Shriver National Institute of Child Health & Human Development or the National Institutes of Health.

Supplemental Materials

Reproducibility Package: doi.org/10.7910/DVN/TB5Q4N.

  • Citation: Lundberg, Ian. 2025. “The Causal Impact of Segregation on a Disparity: A Gap-Closing Approach” Sociological Science 12: 871-890.
  • Received: July 15, 2025
  • Accepted: August 31, 2025
  • Editors: Arnout van de Rijt, Maria Abascal
  • DOI: 10.15195/v12.a35

0

'13 Reasons Why' Probably Increased Emergency Room Visits for Self-Harm among Teenage Girls

By on December 11, 2023 in Articles

Chris Felton

Sociological Science December 11, 2023
10.15195/v10.a33

Abstract

PDF (1795 views)
0 Citation


I present evidence that the release of Netflix’s 13 Reasons Why—a fictional series about the aftermath of a teenage girl’s suicide—caused a temporary spike in emergency room (ER) visits for self-harm among teenage girls in the United States. I conduct an interrupted time series analysis using monthly counts of ER visits obtained from a large, nationally representative survey. I estimate that the show caused an increase of 1,297 self-harm visits (95 percent CI: 634 to 1,965) the month it was released, a 14 percent (6.5 percent, 23 percent) spike relative to the predicted counterfactual. The effect persisted for two months, and ER visits for intentional cutting—the method of suicide portrayed in the series—were unusually high following the show’s release. The findings indicate that fictional portrayals of suicide can influence real-life self-harm behavior, providing support for contagion-based explanations of suicide. Methodologically, the study showcases how to make credible causal claims when effect estimates are likely biased.
Creative Commons LicenseThis work is licensed under a Creative Commons Attribution 4.0 International License.

Chris Felton: Postdoctoral Fellow, Graduate School of Education, Harvard University. This study was completed while the author was a PhD student in the Department of Sociology and Office of Population Research at Princeton University.
E-mail: christopher_felton@gse.harvard.edu

Acknowledgements: For helpful discussions and feedback relevant to this project, I thank (in reverse-alphabetical order) Brandon Stewart, Varun Satish, Momoko Nishikido, Ian Lundberg, Marielle Côté-Gendreau, Dalton Conley, members of the Stewart Lab, the editor, and the anonymous referees. Replication data and code can be found at https://github.com/cmfelton/13rw. All errors are my own.

Supplemental Material

  • Citation: Felton, Chris. 2023. “’13 Reasons Why’ Probably Increased Emergency Room Visits for Self-Harm among Teenage Girls.” Sociological Science 10: 930-963.
  • Received: March 15, 2023
  • Accepted: March 31, 2023
  • Editors: Arnout van de Rijt, Peter Bearman
  • DOI: 10.15195/v10.a33


0

The Population Level Impacts of Differential Fertility Behavior of Parents of Children with Autism

By on August 10, 2015 in Articles

Kinga Makovi, Alix Winter, Ka-Yuet Liu, Peter Bearman

Sociological Science, August 10, 2015
DOI 10.15195/v2.a19

Abstract
PDF (3157 views)
0 Citation

Drawing on population level data of exceptional quality (including detailed diagnostic information on the autism status of sibling pairs of over 3 million different mothers), this study confirms that stoppage is the average fertility response to a child born with autism, thereby reducing observed concordance in sibling pairs and leading to potentially biased estimation of genetic contributions to autism etiology. Using a counterfactual framework and applying matching techniques we show, however, that this average effect is composed of very different responses to suspicion of autism depending on birth cohort, the character of the disorder (severe versus less severe), the gender of the child, poverty status, and parental education. This study also sheds light on when parents suspect autism. We find that parents’ fertility behavior changes relative to matched controls very early after the birth of a child who will later be diagnosed with autism.
Kinga Makovi: Department of Sociology, Columbia University. Email: kinga.makovi@gmail.com.

Alix Winter: Department of Sociology, Harvard University. E-mail: alixsw@gmail.com.

Ka-Yuet Liu: Department of Sociology, University of California, Los Angeles. E-mail:ka@soc.ucla.edu.

Peter Bearman: INCITE, Columbia University. E-mail: psb17@columbia.edu.

Acknowledgements: We thank Keely Cheslack-Postava, Alexandra Brewer, Christine Fountain, and Soumya Mazumdar and the members of the Bearman-Minkoff group for helpful comments on previous drafts. This research is supported by the NIH Director’s Pioneer Award program, part of the NIH Roadmap for Medical Research, through grant number 1 DP1 OD003635-01.

Supplemental Material

  • Citation: Makovi, Kinga, Alix Winter, Ka-Yuet Liu and Peter Bearman. 2015. “The Population Level Impacts of Differential Fertility Behavior of Parents of Children with Autism.” Sociological Science 2: 398-419.
  • Received: January 24, 2014.
  • Accepted: March 13, 2015.
  • Editors: Jesper Sørensen, Stephen L. Morgan
  • DOI: 10.15195/v2.a19

0
SiteLock