Analyze_oneAE: Model selection in logistic regression using...

In masedki/MHTrajectoryR: What the package does (short line)

Description

In this function, we propose to use a logistic regression whose sparsity is viewed as a model selection challenge. Since the model space is huge, a Metropolis-Hastings algorithm carries out the model selection by maximizing the BIC criterion

Usage

Analyze_oneAE(ae, drug, maxit, alpha, nbinit)

Arguments

ae	Binary vector indicate if individual suffers from adverse event (1) or no (0).
drug	Matrix of drugs consumptions. Each row corresponds to one individual drug consumptions.
maxit	Numeric indicating the number of iterations.
alpha	Numeric indicating the size of the neighborhood where the proposal will be uniformly sampled at each iteration. See~http://arxiv.org/abs/1505.03366 for more details.
nbinit	The number of random initializations of the algorithm.

Value

List of detected signals.

Author(s)

Matthieu Marbac and Mohammed Sedki

References

Matthieu Marbac, Pascale Tubert-Bitter, Mohammed Sedki

Bayesian model selection in logistic regression for the detection of adverse drug reactions~http://arxiv.org/abs/1505.03366

masedki/MHTrajectoryR documentation built on May 21, 2019, 12:42 p.m.