top of page
Profile
Join date: Nov 15, 2018
About
Tomas Havranek is Professor at the Institute of Economic Studies, Faculty of Social Sciences, Charles University, Prague. Prior to that appointment he was Advisor to the Board at the Czech National Bank. His research interests include international trade, macroeconomics, monetary policy, energy economics, and methodology of research synthesis. He has published, among other outlets, in the Review of Economics and Statistics, Journal of the European Economic Association, and Journal of International Economics. According to RePEc he is currently the most cited Czech economist. More information is available at tomashavranek.cz and meta-analysis.cz.
Posts (10)
Jul 28, 2026 ∙ 2 min
Two new pre-registered papers: outlier decisions in meta-analysis and AI feedback on meta
My colleagues and I have two new pre-registered papers that may interest MAER-Net members. 1. Do decisions about outliers and influential effects matter? (https://meta-analysis.cz/outliers, https://arxiv.org/abs/2607.23174) With Zuzana Irsova, Martina Luskova, and Tom Stanley, we recompute 358 behavioral science meta-analyses under five outlier treatments: do nothing, drop the most extreme estimate, remove studentized residuals above 3, winsorize at 5/95, and remove estimates with |DFBETAS|...
32
0
3
May 31, 2026 ∙ 1 min
Stress-testing research with AI, now super easy and fully automated
Last December we shared a protocol for stress-testing (meta-)research by making AI models argue and keeping what survives. But running it by hand (opening several models, copying outputs back and forth) is a chore and our original automation via a GPT agent was not reliable. So we automated the protocol using Claude Code. After a one-time setup it is a single sentence: you describe the task, and the skill (built with Zuzana Irsova) has Claude call OpenAI's Codex, runs the critique and...
88
2
4
Dec 12, 2025 ∙ 2 min
Stress-Testing Meta-Research with AI Duels
A practical protocol that makes ChatGPT and Gemini challenge each other to surface edge cases, boundary conditions, and hidden assumptions in meta-analysis. Includes a WAIVE vs MAIVE worked example plus GitHub and DOI links.
427
4
12
Tomas Havranek
Writer
More actions
bottom of page
