CovSel: Model-Free Covariate Selection

Share:

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). 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.

Author
Jenny Häggström, Emma Persson,
Date of publication
2015-11-09 17:23:10
Maintainer
Jenny Häggström <jenny.haggstrom@umu.se>
License
GPL-3
Version
1.2.1

View on CRAN

Man pages

cov.sel
Model-Free Selection of Covariate Sets
cov.sel.np
cov.sel.np
datc
Simulated Data, Continuous
datf
Simulated Data, Factors
datfc
Simulated Data, Mixed
lalonde
Real data, Lalonde
summary.cov.sel
Summary

Files in this package

CovSel
CovSel/inst
CovSel/inst/CITATION
CovSel/NAMESPACE
CovSel/data
CovSel/data/datc.rda
CovSel/data/lalonde.rda
CovSel/data/datf.rda
CovSel/data/datfc.rda
CovSel/R
CovSel/R/summary.cov.sel.R
CovSel/R/cov.sel.R
CovSel/R/cov.sel.np.R
CovSel/MD5
CovSel/DESCRIPTION
CovSel/man
CovSel/man/lalonde.Rd
CovSel/man/cov.sel.Rd
CovSel/man/datc.Rd
CovSel/man/datfc.Rd
CovSel/man/datf.Rd
CovSel/man/summary.cov.sel.Rd
CovSel/man/cov.sel.np.Rd