This package implements two distinct but related statistical approaches to the problem of identifying the combinations of medication error characteristics that are more likely to result in harm: 1) Bayesian hierarchical models with optimal Bayesian ranking on the log odds of harm, and 2) an empirical Bayes model that estimates the ratio of the observed count of harm to the count that would be expected if error characteristics and harm were independent. In addition, for the Bayesian hierarchical model, the package provides functions to assess the sensitivity of results to different specifications of the random effects distributions.

Package: | mederrRank |

Type: | Package |

Version: | 0.0.6 |

Date: | 2011-05-03 |

License: | GPL 2 or greater |

LazyLoad: | yes |

The package is loaded with the usual `library(mederrRank)`

command. The most important functions are `bhm.mcmc`

, `bhm.resample`

and `mixnegbinom.em`

.

Sergio Venturini sergio.venturini@unibocconi.it,

Jessica A. Myers jmyers6@partners.org

Myers, J. A., Venturini, S., Dominici, F. and Morlock, L. (2011), "Random Effects Models for Identifying the Most Harmful Medication Errors in a Large, Voluntary Reporting Database". Technical Report.

`bayes.rank`

,
`bhm.mcmc`

,
`bhm.resample`

,
`mixnegbinom.em`

.

Questions? Problems? Suggestions? Tweet to @rdrrHQ or email at ian@mutexlabs.com.

Please suggest features or report bugs with the GitHub issue tracker.

All documentation is copyright its authors; we didn't write any of that.