Model-free covariate selection
Model-free selection of covariates under unconfoundedness for situations where the parameter of interest is an average causal effect. This package is based on model-free backward elimination algorithms proposed in de Luna, Waernbaum and Richardson (2011, Biometrika). Marginal co-ordinate hypothesis testing is used in situations where all covariates are continuous while kernel-based smoothing appropriate for mixed data is used otherwise; see Persson et al. (2017) and Häggström et al. (2015).
Link to CRAN-R.
Model-free selection of covariates in high dimensions under unconfoundedness for situations where the parameter of interest is an average causal effect. This package is based on model-free backward elimination algorithms proposed in de Luna, Waernbaum and Richardson (2011) and VanderWeele and Shpitser (2011). Confounder selection can be performed via either Markov/Bayesian networks, random forests or LASSO; see Häggström (2017).
Link to CRAN-R
References:
SLIDES from invited talk at Joint Statistical Meeting in Seattle, 2015.
de Luna, X., Waernbaum, I., and Richardson, T. (2011) Covariate selection for the non-parametric estimation of an average treatment effect, Biometrika, 98, 861-875.
Häggström, J. (2017). Data-driven Confounder Selection via Markov and Bayesian Networks (with discussion). Biometrics, dog: 10.1111/biom.12788.
Preprint: arXiv:1604.07212
Häggström, J., Persson, E., Waernbaum, I., & de Luna, X. (2015). CovSel: An R Package for Covariate Selection When Estimating Average Causal Effects. Journal of Statistical Software, 68(1), 1 - 20. doi:http://dx.doi.org/10.18637/jss.v068.i01
Persson, E., Häggström, J., Waernbaum, I., & de Luna, X. (2016). Data-driven algorithms for dimension reduction in causal inference. Computational Statistics & Data Analysis, 105, 280-292. Preprint. arXiv:1309.4054