Levi

Levente Littvay (Levi) is a Research Professor at ELTE Centre for Social Sciences and a Senior Visiting Researcher at the Democracy Institute of Central European University, where he also used to be Professor of Political Science (2007-2023) and taught graduate courses in research design, applied statistics, electoral politics, voting behavior, political psychology, and American politics. He is the inaugural and only two-time recipient of CEU’s Teaching Award (2015 for methods-, and 2021 for online teaching). Received his MA and PhD in Political Science and an MS in Survey Research and Methodology from the University of Nebraska-Lincoln. Taught numerous research methods workshops globally and online, and was one of the Academic Convenors of the European Consortium for Political Research Methods Schools (2015-21), is the founder of MethodsNET, former 9-year presidium member of the Hungarian Political Science Association and head of Team Survey in Team Populism where he helped spawn the Leader Profile Series and the New Populism series with The Guardian and co-produced both the MethodsNET and Team Populism YouTube channels during the COVID-19 lockdowns. He was a member of the European Social Survey’s Round 10 (2020-21) democracy and COVID-19 module and CRONOS II Populism and Technocracy questionnaire design teams. Secured over a million and a half EUR in grants to conduct research on AI, survey and quantitative methodology, twin and family studies, and the psychology of radicalism and populism. His current project received over 400,000 EUR from the Hungarian National Research, Development, and Innovation Office Excellence 2025 grant to explore the use of large language models for public opinion research. Other awards include ISPP’s 2025 John L. Sullivan Mentor Prize, the 2022 Giovanni Sartori Prize for best article in the Italian Political Science Review, European University Institute’s Fernand Braudel Senior Research Fellowship (2019-20), and the Morton Deutsch Award for best 2017 article in Social Justice ResearchHe is also published in Political AnalysisThe Journal of PoliticsPolitical Research QuarterlyPolitical PsychologyBMC Medical Research Methodology, and, along with other medical journals, in Twin Research and Human Genetics, where he is Associate Editor for Social Sciences. Books include Contemporary US Populism in Comparative Perspective with Kirk Hawkins in Cambridge University Press’s Elements Series and Multilevel Structural Equation Modeling with Bruno Castanho Silva and Constantin Manuel Bosancianu in SAGE’s QASS (little green book) series, which was also published in Chinese.

Research & Impact

Current Research Agenda:

    1. Improve accessibility & appropriate use of mainly multilevel & structural equation models.
    2. Advance research on populist polarization, namely the measurement & mitigation of partisan motivated democracy eroding policy preferences.
    3. Understand motivations underlying secessionist attitudes.

Impact Statement:

    1. In the past decade I have led one of the largest political science methods education centers that, during this time, was responsible for the training of around 10,000 participants. In 2021 I (co-)founded MethodsNET to advance pluralistic social science methods. I lead the development of the MethodsNET YouTube Channel.
    2. I am committed to producing publicly available data which lead to my participation in the European Election Study (mainly 2009), Comparative Study of Election Systems (contributing Hungary 2018 & Tunisia 2019), European Social Survey Wave 10 Democracy & COVID Questionnaire Design Teams. I also extended the Global Populism Database w/ US Governors data & led the revival of the Hungarian Twin Registry and its extension into a population based research resource.
    3. Through my efforts in Team Populism, I helped improve public understanding of populism, spawning our YouTube channel, the Leader Profile Series (with online training program), and The Guardian’s 84 article New Populism series. Based on my research, I proposed and designed the most visited piece in the series: “How Populist Are You?” (with over 1.5 million views).

Workshops

Workshops: (1) Social Science Research Design, (2) AI/LLM Life Skills for Academics, (3) Survey Research Methods, (4) Measurement in the Social Sciences, (5) Logic of Causal Inference (Intro to Impact Evaluation), (6) Intro to Experimental Social Science, (7) Intro to Stats, (8) Data Theory & Literacy, (9) Data Visualization Basics, (10) R, (11) Introduction to Regression (OLS, Assumptions, Logistic), (12) Regression 2 (GLM, Weights, Clusters / Voting Behavior Methods), (13) Advanced Topics in Regressions, (14) Multilevel Modeling, (15) Structural Equation Modeling, (16) Advanced Topics in Structural Equation Modeling, (17) Multilevel Structural Equation Modeling, (18) Latent Variable Models, (19) Mplus, (20) Missing Data. Retired Workshops: (21) Ecological Inference, (22) Introduction to Categorical Data Analysis, (23) Multivariate Statistics. In preparation: (24) Introduction to Quantitative Text Analysis. (25) Introduction to Machine Learning.

I always struggled with math, so I had to develop understandings and intuitions that ran parallel to the painstakingly acquired mathematical understandings of quantitative methods. This made me an effective educator of advanced topics to non-mathematical social science or policy audiences. In my teaching, I focus on theory, design, and effective communication and emphasize understanding both math and software applications while rejecting point-and-click or code, copy-and-paste solutions.

Methodological Applications

Design effective studies and apply the appropriate methodologies to real life problems in the world of policy, science and beyond. Produce studies that allow for causal inference to maximize effective resources use.

Tools used include randomized experiments, counterfactual program evaluation and other applications of quasi-experimental designs for causal inference, survey design and analysis, nonresponse correction, structural equation and multilevel models, and general foundations in the philosophy of science.

Blog

OpenAI’s GPT-OSS is Another Deepseek Moment (But Not the Way You Think)

OpenAI released its first open models. (#irony) And the whole AI space is going crazy. GPT-OSS models are off the charts in the benchmarks, matching or even beating some of the leading models out there, including leading OpenAI models (at least for a few more days when they release something big). And yes, we do …

Something has gone terribly wrong with academic administration of privacy and ethics

Today, I was asked to submit a data processing plan for a project that uses anonymized survey data downloadable from the Internet by anyone (3%) and computer-simulated data (97%). Admittedly, the European Social Survey (and similar) was collected on humans, but it was released after careful anonymization, and the data collection was done with careful …

Bamberg Keynote, April 2025

On April 7, 2025, I gave a keynote at the BAGSS Methods Institute on AI. For those who wish to see the slides again for reference, they are here. And here is the podcast Notebook LM produced about my grant application.