PVM
is an R
package containing a wide variety of methods used in the field of pharmacovigilance for discovering 'interesting' drug-adverse event pairs from spontaneous reporting data.
The methods currently implemented are:
the reporting odds ratio (ROR), see R/ROR.R
;
Yule's Q, see R/YulesQ.R
;
the proportional relative risk (PRR), see R/PRR.R
;
the relative report rate (RRR), see R/RRR.R
;
the reporting Fisher's exact test (RFET) and the mid-p-value test (midRFET), see R/fisherExactTest.R
;
the chi-squared test (with and without Yates' correction for continuity), see R/chi2Test.R
;
the binomial likelihood ratio test, see R/logLikelihoodRatioBinomial.R
;
the test of the Poisson mean, see R/PoissonTest.R
;
the Bayesian confidence propagation neural network (BCPNN), see R/BCPNN.R
;
the Gamma Poisson shrinker (GPS), see R/GPS.R
, and
the LASSO, see R/LASSO.R
To install, simply type in R
devtools::install_github("bips-hb/pvm")
We gratefully acknowledge the financial support from the innovation fund (“Innovationsfonds”) of the Federal Joint Committee in Germany (grant number: 01VSF16020).
Please cite
Adverse Drug Reaction or Innocent Bystander? A Systematic Comparison of Statistical Discovery Methods for Spontaneous Reporting Systems\ L.J. Dijkstra, M. Garling, R. Foraita & I. Pigeot\ Pharmacoepidemiology and Drug Safety (2020)\ DOI:10.1002/PDS.4970
Louis Dijkstra\ Leibniz Institute for Prevention Research & Epidemiology E-mail: dijkstra (at) leibniz-bips.de
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.