Bayesian Methods for Identifying the Most Harmful Medication Errors
Optimal Bayesian Ranking
Markov Chain Monte Carlo Estimation (Step 2) of the Bayesian Hierarchi...
Markov Chain Monte Carlo Estimation (Step 1) of the Bayesian Hierarchi...
Resampling Transformation for the Markov Chain Monte Carlo Estimation ...
The Negative Binomial Mixture Distribution
The Negative Binomial Distribution
The Skewed Student t Distribution
Geometric Mean of the Relative Risk Empirical Bayes Posterior Distribu...
Log-Likelihood Difference for the Parameters
Log-Likelihood Difference for the Parameters
Negative Log-Posterior Function of the Bayesian Hierarchical Model for...
Unnormalized Marginal Posterior Distributions for and
Class "mederrData". Data Specification for Identifying the Most Harmfu...
Class "mederrFit". Simulated Monte Carlo Chains (Step 1) for the Bayes...
tools:::Rd_package_title("mederrRank")
Class "mederrResample". Simulated Monte Carlo Chains (Step 2) for the ...
Expectation-Maximization Algorithm for the Mixture of Negative Binomia...
Log-Likelihood Function for the Mixture of Negative Binomial Distribut...
Log-Likelihood Score Function for the Mixture of Negative Binomial Dis...
Expectation-Maximization Algorithm for the Negative Binomial Distribut...
Log-Likelihood Function for the Mixture of Negative Binomial Distribut...
Log-Likelihood Score Function for the Negative Binomial Distribution
Posterior Predictive Test statistics
Plot of Medication Error Data and Analysis
Posterior Predictive Data Replications
The Negative Binomial Mixture Distribution
Summary of Medication Error Data and Analysis
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 are implemented in this package: 1) a Bayesian hierarchical model 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.