Causal Inference (CAUSE)
In an era characterized by the exponential growth of data complexity and the increasing need for evidence-based decision-making, the field of causal inference [1] has emerged as a pivotal and rapidly evolving area of research. Methodological research in causal inference aims to equip domain scientists with tools to move beyond mere correlations and conduct data analyses that discern and quantify the effects of the true drivers of observed outcomes [2]. Such progress relies on rigorous causal models that facilitate inference about the effects of interventions, combined with meticulous statistical uncertainty assessment. The broader significance of causal discovery and inference lies in their transformative potential across multiple disciplines. By disentangling cause-and-effect relationships from mere associations, researchers can uncover the underlying mechanisms governing complex phenomena across domains such as biomedical discoveries, social sciences, and public policy [3]. In this way, causal analyses provide a solid foundation for evidence-based practices and interventions.
This Focus Topic serves as a platform for collaboration and knowledge exchange between researchers engaged in advancing the methodological and theoretical foundations of causal inference, and domain scientists at TUM. A particular focus lies on the domains of climate science [4], computational biology [5], and economics [6], which feature rich and complex data sources that constitute not only a fertile ground for application of techniques from causal inference but also prompt new methodological challenges [7].
[1] Pearl, Judea. Causality. Cambridge University Press, 2009.
[2] Hernán, Miguel A., and James M. Robins. Causal inference. CRC Press, 2010.
[3] Imbens, Guido W., and Donald B. Rubin. Causal inference in statistics, social, and biomedical Sciences. Cambridge University Press, 2015.
[4] Runge, Jakob, et al. "Inferring causation from time series in Earth system sciences." Nature Communications 10.1 (2019): 2553.
[5] Rivas-Barragan, Daniel, et al. "Drug2ways: Reasoning over causal paths in biol. networks for drug disc." PLoS Computational Biology 16.12 (2020).
[6] Athey, Susan and Imbens, Guido W. “The state of applied econometrics: causality and policy eval.” Journal of Economic Perspectives 31.2 (2017): 3-32.
[7] Schölkopf, Bernhard, et al. "Toward causal representation learning." Proceedings of the IEEE 109.5 (2021).