论文信息 - Discussion of "The Blessings of Multiple Causes" by Wang and Blei

Discussion of "The Blessings of Multiple Causes" by Wang and Blei

This commentary has two goals. We first critically review the deconfounder method and point out its advantages and limitations. We then briefly consider three possible ways to address some of the limitations of the deconfounder method.

Zhichao Jiang | Kosuke Imai | Zhichao Jiang | K. Imai

[1] C. Matias,et al. Identifiability of parameters in latent structure models with many observed variables , 2008, 0809.5032.

[2] David R. Cox,et al. Principles of Applied Statistics , 2011 .

[3] P. Spirtes,et al. Causation, prediction, and search , 1993 .

[4] Edward H. Kennedy. Nonparametric Causal Effects Based on Incremental Propensity Score Interventions , 2017, Journal of the American Statistical Association.

[5] Michael I. Jordan,et al. Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[6] J. Wooldridge. Control Function Methods in Applied Econometrics , 2015, The Journal of Human Resources.

[7] M. Hudgens,et al. Toward Causal Inference With Interference , 2008, Journal of the American Statistical Association.

[8] Alexander D'Amour,et al. On Multi-Cause Causal Inference with Unobserved Confounding: Counterexamples, Impossibility, and Alternatives , 2019, ArXiv.

[9] G. Imbens,et al. Identification and Estimation of Triangular Simultaneous Equations Models without Additivity , 2002 .

[10] S. Geneletti. Identifying direct and indirect effects in a non‐counterfactual framework , 2007 .

[11] Joshua D. Clinton,et al. The Statistical Analysis of Roll Call Data , 2004, American Political Science Review.

[12] J. Kruskal. Three-way arrays: rank and uniqueness of trilinear decompositions, with application to arithmetic complexity and statistics , 1977 .