dstat: Conditional Sensitivity Analysis for Matched Observational Studies

A d-statistic tests the null hypothesis of no treatment effect in a matched, nonrandomized study of the effects caused by treatments. A d-statistic focuses on subsets of matched pairs that demonstrate insensitivity to unmeasured bias in such an observational study, correcting for double-use of the data by conditional inference. This conditional inference can, in favorable circumstances, substantially increase the power of a sensitivity analysis (Rosenbaum (2010) <doi:10.1007/978-1-4419-1213-8_14>). There are two examples, one concerning unemployment from Lalive et al. (2006) <doi:10.1111/j.1467-937X.2006.00406.x>, the other concerning smoking and periodontal disease from Rosenbaum (2017) <doi:10.1214/17-STS621>.

Version: 1.0.4
Imports: stats
Published: 2019-04-16
DOI: 10.32614/CRAN.package.dstat
Author: Paul R. Rosenbaum
Maintainer: Paul R. Rosenbaum <rosenbaum at wharton.upenn.edu>
License: GPL-2
NeedsCompilation: no
In views: CausalInference
CRAN checks: dstat results


Reference manual: dstat.pdf


Package source: dstat_1.0.4.tar.gz
Windows binaries: r-devel: dstat_1.0.4.zip, r-release: dstat_1.0.4.zip, r-oldrel: dstat_1.0.4.zip
macOS binaries: r-release (arm64): dstat_1.0.4.tgz, r-oldrel (arm64): dstat_1.0.4.tgz, r-release (x86_64): dstat_1.0.4.tgz, r-oldrel (x86_64): dstat_1.0.4.tgz


Please use the canonical form https://CRAN.R-project.org/package=dstat to link to this page.