PLUE: Profiled Likelihood Uncertainty Estimation

Description Usage Arguments Details References

View source: R/PLUE.R

Description

Performs a likelihood-based uncertainty estimation on a model. This analysis consists on a Metropolis Monte Carlo exploration of the parameter space and subsequent profiling of model results based on the likelihood of the input parameters.

Usage

1
2
3
4
5
6
7
8
9
PLUE(model = NULL, factors, N, LL, start, res.names = NULL,
  method = c("internal", "mcmc"), opts = list(), nboot = 0,
  repetitions = 1, cl = NULL)

## S3 method for class 'PLUE'
print(x, ...)

## S3 method for class 'PLUE'
plot(x, ...)

Arguments

model

The function to be run, representing the model or simulation.

factors

The names of the input variables (used for naming the 'data' data.frame and in plotting) Either a vector of strings or a single number representing the number of factors

N

The number of samples to be generated by the Metropolis algorithm.

LL

The POSITIVE Likelihood function to be used by the Metropolis algorithm. It must accept an array with length equal to the number of factors.

start

The initial point to be evaluated. Must have the same length as the number of factors.

res.names

Optional: what are the names of the model results? (Used mainly for plotting)

method

May be either "internal", which runs a naive and inneficient algorithm provided for test and didatic purposes, or "mcmc", which will run the metrop function from the mcmc package.

opts

Further options to be passed to the Metropolis function. See the help on metrop.

nboot

Number of bootstrap replicates for calculating the PRCC.

repetitions

The number of model repetitions to be run for a single data point. See the vignette on stochastic models for details

cl

Cluster generated with the “parallel” library. May be of any type supported. If a cluster is provided, the model will be run in parallel or distributed across the cluster via clusterApply. No load balancing is provided, so the model results are reproducible.

NOTE: You should manually export ALL objects required for the model to run, including the model function itself. See the help on clusterExport on package parallel for details.

x

An LHS/PLUE object. For "tell", an incomplete LHS object (created with model=NULL)

...

Currently ignored

Details

A detailed description can be found on Chalom & Prado (2015).

References

Chalom, A. and Prado, P.I.K.L. 2015. Uncertainty analysis and composite hypothesis under the likelihood paradigm. arXiv:1508.03354 [q-bio.QM]


pse documentation built on May 2, 2019, 12:56 a.m.