GESIS Leibniz Institute for the Social Sciences, visit homepage

GESIS Training

Causality in the Social Sciences III – Heterogeneous Causal Effects



The workshop was organized by Sebastian E. WenzNora Müller, and Klaus Pforr of GESIS – Leibniz Institute for the Social Sciences. Funding from the Akademie für Soziologie and GESIS is greatfully acknowledged. 

The workshop Causality in the Social Sciences III – Heterogeneous Causal Effects took place 14-15 October 2021 online only (via Zoom).   


  • Jennie E. Brand, Professor of Sociology and Statistics at the University of California, Los Angeles (UCLA), and Director of the California Center for Population Research (CCPR) and Co-Director of the Center for Social Statistics (CSS) at UCLA.
  • Richard Breen, Professor of Sociology at the University of Oxford and Fellow of Nuffield College.
  • Saskia le Cessie, Professor of Statistical Methods in Observational (Clinical) Epidemiological Research, Universiteit Leiden.

Please scroll down or click on the following links to read the Call for Applications, look at the Workshop Program, learn about the Venue, Registration, or how to Contact us. You’ll find all relevant information about the workshop on this website.

Because this is a past event, this website will no longer be updated. 

Call for Applications

Causality lies at the heart of any scientific explanation: Understanding how an intervention or treatment did or would change the course of the world or how a particular state of the world came about, requires an understanding of cause and effect. The currently dominant perspective of counterfactual causality was subject of two workshops funded by the Akademie für Soziologie in 2019 and 2020. The workshop “Causality in the Social Sciences III – Heterogeneous Causal Effects” builds on both by addressing a specific topic in causal inference that is nevertheless fundamental to all social sciences, namely effect heterogeneity. 

Effect heterogeneity is present whenever individual-level causal effects deviate from the average effect, for example, when individuals—or any other unit of observation—differ in their response to an intervention or treatment. Across different social science disciplines, researchers have concluded that ignoring existing effect heterogeneity can lead to incorrect conclusions when testing hypotheses and to inefficient or even harmful policy recommendations (Bolger et al. 2019; Imai and Strauss 2011; Morgan 2001; Angrist 2004; Heckman, Smith, and Clements 1997). On the other hand, incorrectly specified models—e.g., models that do not fully account for selection bias—may detect heterogeneous effects when the true effect is homogeneous (Breen, Choi, and Holm 2015).  

Traditionally, social scientists have been tackling effect heterogeneity mainly through interaction terms. While this simple approach can be effective, it is not without limitations and pitfalls (e.g., Mize 2019). Recently, technically more advanced and substantively different approaches—e.g., parametric and nonparametric techniques based on propensity scores, quantile regression models—have gained popularity and are subject of ongoing debates about their potential and limitations (Breen, Choi, and Holm 2015; Killewald and Bearak 2014; Xie, Brand, and Jann 2012). 

The workshop “Causality in the Social Sciences III” picks up on these recent approaches and debates from three different angles: 

  1. It’s complicated: Interpretation of heterogeneous effects  

  2. Estimating heterogeneous effects with observational and experimental data  

  3. Machine learning techniques for specification search  

The two-day workshop aims to provide opportunities for exchange and discussions about ongoing substantial and methodological research tackling one or several of these three specific topics. Confirmed keynotes will be delivered by Jennie E. Brand, Professor of Sociology and Statistics at UCLA, Richard Breen, Professor of Sociology at the University of Oxford and Fellow of Nuffield College, and Saskia le Cessie, Professor of Statistical Methods in Observational (Clinical) Epidemiological Research, Universiteit Leiden.

Besides these general talks, early career researchers (PhD students and PostDocs) have the opportunity to present, discuss, and reflect on how far aspects of heterogeneity in causal effects are relevant for their research (10 minutes for presentation and 20 minutes for discussion). Each presentation will be discussed by the invited keynote speakers as well as the workshop participants. In addition, each participant is expected to thoroughly discuss two previously assigned papers that he or she will have to read before the workshop.  

A maximum of 15 presentations will be accepted. The workshop is supported by the German Akademie für Soziologie and GESIS – Leibniz Institute for the Social Sciences. Workshop participation is free of charge. However, travel, accommodation, as well as lunch and dinner expenses, cannot be covered. Priority in admission will be given to members of the Akademie für Soziologie. 

Please send your applications via e-mail to no later than 30 June 2021.  

Your application should include  

a) an abstract of the paper that will be presented (up to 500 words); 

b) a brief CV (up to one page). 

Confirmations about acceptance will be sent out by 31 July 2021 at the latest. Accepted participants will be asked to submit a full paper draft or extended abstract four weeks prior to the workshop and discuss two papers from other participants.  

Further information on the workshop will be provided on the following website:  

We are looking forward to your contribution and to welcoming you at GESIS in Mannheim or online: 

  • If meeting in person will not be possible due to the state of the Covid-19 pandemic in Mannheim and Germany, the workshop will be held online only.  

  • If meeting in person is possible, participants may join us at GESIS in Mannheim or online, according to their preferences.  

Please send all remaining questions to causality-workshop(at)gesis(dot)org.


The full program can be downloaded here (pdf). (194 kB)

14 October 2021 (Thursday)


15 October 2021 (Friday)



Wrap up/Opening



Talk 9: Oliver Rittmann (University of Mannheim): “The Parliamentary Attention Deficit Disorder”

Discussants: Classe & Levi




Talk 10: Franz Classe/Christoph Kern (IHF, Munich): “Latent Variable Effect Forests”

Discussants: Levi & Mele


Keynote 1: Richard Breen (University of Oxford): “Heterogeneous Causal Effects: Identification and Interpretation”.




Talk 11: Sara Kalucza (Umeå University): “Does Anyone Suffer from Teenage Motherhood? Mental Health Effects of Teen Motherhood in the UK Are Small and Homogeneous”

Discussants: Bering & Zhou



Talk 12: Sebastian Levi/Ingo Wolf (Hertie School, Berlin): “How Does Information Provision Affect Support for Climate Change Policies in the Transport Sector?”

Discussants: Classe & Rittmann



Talk 1: Kevin P. Schönholzer (University of Zurich): “Educational Inequality: Life-Course Outcomes of Welfare State Policy”

Discussants: Lang/Schwabe & Mele




Talk 2: Gabriele Mari (Erasmus University Rotterdam): “The Timing of Parental Unemployment, Insurance, and Children’s Education in the Netherlands”

Discussants: Haupt & Schönholzer





Keynote 3: Saskia le Cessie (Universiteit Leiden): “On causal questions and principled answers”.




Wrap up morning/opening afternoon


Talk 13: Paul C. Bauer/ Camille Landesvatter (MZES, Mannheim): “Ideal Research Designs: Using Constraint-Free Thought Experiments to Benchmark Designs for Causal Questions”

Discussants: Kalucza & Rittmann

Talk 3: Francesca Mele (University of Zurich): “Agency in Secondary School Transitions in Switzerland: To What Extent Can Children Pursue Their Own Path?”

Discussants: Haupt & Kalucza



Talk 14: Ang Yu (University of Wisconsin, Madison): “Causal Decomposition with Effect Heterogeneity”

Discussants: Bauer/Landesvatter & Zhou

Talk 4: Sebastian Lang/ Ulrike Schwabe (DZHW, Hannover): “The German Initiative of Excellence: Short- and Mid-Term Effects on Students’ Perceptions of Educational Quality”

Discussants: Conte Keivabu & Schönholzer



Talk 15: Xiang Zhou (Harvard University): “Attendance, Completion, and Heterogeneous Returns to College”

Discussants: Bauer/Landesvatter & Yu



Talk 5: Henriette Bering/Wiebke Schulz (University of Bremen): “Does the Impact of Extracurricular Activities Vary by Parental Socioeconomic Status? An Analysis of Adolescents’ Cognitive Skills”

Discussants: García Sierra & Mari




Talk 6: Alicia García Sierra (University of Oxford): “Heterogeneous Parental Responses to Children’s Early Health Disadvantages”

Discussants: Bering & Conte Keivabu


Summary: Richard Breen (University of Oxford)





Talk 7: Risto Conte Keivabu (EUI): “The Big Plunge: How Environmental Policy Lifts School Attendance for the Poor”

Discussants: Lang/Schwabe & Mari



Talk 8: Andreas Haupt (KIT Karlsruhe): “Who profits from occupational licensing?”

Discussants: García Sierra & Yu






Keynote 2: Jennie E. Brand (University of California, Los Angeles):

“Uncovering College Effect Heterogeneity”.






Virtual Drinks




The workshop took place online only (via Zoom).


Active participants (those who are invited to present a paper): Once we have accepted your paper, we let you know via email how to register for the event.

Passive participants (those who are interested in participating without presenting a paper): Send an email to causality-workshop(at)gesis(dot)org and simply let us know that you would like to participate without presenting. We will then confirm your registration as a passive participant ASAP and send you Zoom login credentials in due time.



The workshop “Causality in the Social Sciences III – Heterogeneous Causal Effects” was organized by Sebastian E. WenzNora Müller, and Klaus Pforr of GESIS – Leibniz Institute for the Social Sciences.

Please send all your questions to causality-workshop(at)gesis(dot)org