submax-package {submax}

Effect Modification in Observational Studies Using the Submax Method

Description

Effect modification occurs if a treatment effect is larger or more stable in certain subgroups defined by observed covariates. The submax or subgroup-maximum method of Lee et al. (2017) <arXiv:1702.00525> does an overall test and separate tests in subgroups, correcting for multiple testing using the joint distribution.

Details

The DESCRIPTION file:

Package:	submax
Type:	Package
Title:	Effect Modification in Observational Studies Using the Submax Method
Version:	1.1.1
Author:	Paul R. Rosenbaum
Maintainer:	Paul R. Rosenbaum <[e-mail]>
Description:	Effect modification occurs if a treatment effect is larger or more stable in certain subgroups defined by observed covariates. The submax or subgroup-maximum method of Lee et al. (2017) <arXiv:1702.00525> does an overall test and separate tests in subgroups, correcting for multiple testing using the joint distribution.
Imports:	stats, mvtnorm, sensitivityfull
License:	GPL-2
Encoding:	UTF-8
LazyData:	true

Index of help topics:

Active                  Physical Activity and Survival in NHANES
amplify                 Amplification of sensitivity analysis in
                        observational studies.
mercury                 NHANES Mercury/Fish Data
mscorev                 Computes M-scores for Permuational M-tests.
score                   Creates M-scores for Use by submax().
separable1fc            Computes the Separable Approximation.
submax                  Effect Modification Using the Submax Method in
                        Observational Studies
submax-package          Effect Modification in Observational Studies
                        Using the Submax Method
tbmetaphase             Genetic damage from drugs used to treat TB

The main function is submax(). Also helpful is score(). See their documentation.

Author(s)

Paul R. Rosenbaum

Maintainer: Paul R. Rosenbaum <[e-mail]>

References

Lee, K., Small, D. S., & Rosenbaum, P. R. (2017). A new, powerful approach to the study of effect modification in observational studies. arXiv preprint arXiv:1702.00525.

Examples

#Reproduces parts of Table 2 of Lee et al. (2017)
data(Active)
submax(Active$delta,Active[,1:7],gamma=1.70,alternative="less")