The Causual Nature of Modeling in Data-Intensive Science - a podcast by MCMP Team

Wolfgang Pietsch (MCTS/TU Munich) gives a talk at the MCMP Colloquium (3 June, 2015) titled "The Causual Nature of Modeling in Data-Intensive Science". Abstract: Abstract: I argue for the causal character of modeling in data-intensive science, contrary to wide-spread claims that big data is only concerned with the search for correlations. After introducing and discussing the concept of data-intensive science, several algorithms are examined with respect to their ability to identify causal relationships. To this purpose, a difference-making account of causation is proposed that broadly stands in the tradition of David Lewis’s counterfactual approach, but fits better the type of evidence used in data-intensive science. The account is inspired by causal inferences of the Mill’s method type. I situate data-intensive modeling within a broader framework of a Duhemian or Cartwrightian scientific epistemology, drawing an analogy to exploratory experimentation.

Further episodes of MCMP – Philosophy of Science

Further podcasts by MCMP Team

Website of MCMP Team