Regression by dependence minimization and its application to causal inference in additive noise models

This paper presents a new statistical toolkit by applying three techniques for data-driven causal inference from the machine learning community that are little-known among economists and innovation scholars: a conditional independence-based approach, additive noise models, and non-algorithmic inference by hand. We include three applications to CIS data to investigate public funding schemes for R&D investment, information sources for innovation, and innovation expenditures and firm growth. Preliminary results provide causal interpretations of some previously-observed correlations. Our statistical 'toolkit' could be a useful complement to existing techniques.

Download Full-text

Modeling confounding by half-sibling regression

Proceedings of the National Academy of Sciences ◽

10.1073/pnas.1511656113 ◽

2016 ◽

Vol 113 (27) ◽

pp. 7391-7398 ◽

Cited By ~ 7

Author(s):

Bernhard Schölkopf ◽

David W. Hogg ◽

Dun Wang ◽

Daniel Foreman-Mackey ◽

Dominik Janzing ◽

...

Keyword(s):

Time Series ◽

Causal Inference ◽

Recent Work ◽

Additive Noise ◽

Time Series Data ◽

Series Data ◽

Theoretical Justification ◽

Quantity Of Interest ◽

Noise Models ◽

Half Sibling

We describe a method for removing the effect of confounders to reconstruct a latent quantity of interest. The method, referred to as “half-sibling regression,” is inspired by recent work in causal inference using additive noise models. We provide a theoretical justification, discussing both independent and identically distributed as well as time series data, respectively, and illustrate the potential of the method in a challenging astronomy application.

Download Full-text

Causal Inference for Mixed-Type Data in Additive Noise Models

Neural Information Processing - Lecture Notes in Computer Science ◽

10.1007/978-3-030-63833-7_19 ◽

2020 ◽

pp. 223-234

Author(s):

Xin Liu ◽

Zenglin Xu ◽

Ping Guo

Keyword(s):

Causal Inference ◽

Mixed Type ◽

Additive Noise ◽

Type Data ◽

Noise Models

Download Full-text

Nonequilibrium Phenomena in Globally Coupled Phase Oscillators: Noise-Induced Bifurcations, Clustering, and Switching

International Journal of Bifurcation and Chaos ◽

10.1142/s0218127497000728 ◽

1997 ◽

Vol 07 (04) ◽

pp. 917-922

Author(s):

Seon Hee Park ◽

Seunghwan Kim ◽

Seung Kee Han

Keyword(s):

Phase Transition ◽

Noise Intensity ◽

Multiplicative Noise ◽

Additive Noise ◽

Critical Value ◽

Phase Oscillators ◽

Deterministic Systems ◽

Nonequilibrium Phenomena ◽

Noise Models ◽

Coupled Phase Oscillators

The Nonequilibrium phenomena in a class of globally coupled phase oscillators systems with multiplicative noise are studied. It is shown that at the critical value of the noise intensity the systems undergo a phase transition and converge to clustered states. We also show that the time delay in the interaction between oscillators gives rise to the switching phenomena of clusters. These phenomena are noise-induced effects which cannot be seen in the deterministic systems or in the simple additive noise models.

Download Full-text