LBOptionsMCMC-class: Class "LBOptionsMCMC" - Specification of MCMC estimation in...
In RLadyBug: Analysis of Infectious Diseases using Stochastic Epidemic Models

Description Objects from the Class Slots Extends Methods Author(s) See Also Examples

Specification of MCMC estimation in SEIR models.

Objects can be created by calls of the form new("LBOptionsMCMC", seed, LBmodel, ignoreData, initBeta, initBetaN, initIncu, initInf, initDia, algo, randomWalk).

algo:

Object of class "vector". Contains a specification of the MCMC algorithm, i.e. a vector with names

`samples`	how many? (without burnin)
`thin`	how to thin the random numbers
`burnin`	the first x random numbers will be ignored

randomWalk:

Object of class "vector". Contains a specification of the random walk, i.e. a vector with names

`betaRWsigma`	sigma concerning parameter β
`betaNRWsigma`	sigma concerning parameter β_n
`gammaERWsigma`	sigma concerning parameter γ of the gamma distribution of the incubation time
`deltaERWsigma`	sigma concerning parameter δ of the gamma distribution of the incubation time
`gammaIRWsigma`	sigma concerning parameter γ of the gamma distribution of the infectious time
`deltaIRWsigma`	sigma concerning parameter δ of the gamma distribution of the infectious time
`gammaDRWsigma`	sigma concerning parameter γ of the gamma distribution of the seroconversion time
`deltaDRWsigma`	sigma concerning parameter δ of the gamma distribution of the seroconversion time
`ERWsigma`	sigma concerning unknown exposure times

seed:

Object of class "numeric". The seed value to use when calling the Java program

LBmodel:

Object of class "vector". Contains a specification of the SEIR model, i.e. a vector with names

`incuTimePDF`	distribution of incubation time
`infTimePDF`	distribution of the infectious time
`diagTimePDF`	distribution of the seroconversion time
`meanVar`	mean variance representation of periods (TRUE/FALSE)

ignoreData:

Object of class "vector". Booleans

`ignoreE`	Ignore the specified exposure (E) event times
`ignoreI`	Ignore the specified infective (I) event times
`ignoreD`	Ignore the specified diagnose (D) event time

initBeta:

Object of class "list". Inital values:

`init`	for β
`gamma`	for the priori parameter γ
`delta`	for the priori parameter δ

initBetaN:

Object of class "list". Inital values:

`init`	for β_n
`gamma`	for the priori parameter γ
`delta`	for the priori parameter δ

initIncu:

Object of class "list". Initial values:

`g`	for parameter γ of the gamma distribution of the incubation time
`g.gamma`	for the parameter gamma of the distribution of g
`g.delta`	for the parameter delta of the distribution of g
`d`	for parameter δ of the gamma distribution of the incubation time
`d.gamma`	for the parameter gamma of the distribution of d
`d.delta`	for the parameter delta of the distribution of d

or choose asis or constant:

`asis`	TRUE/FALSE
`const`	TRUE/FALSE
`const.val`	value of constant if `const` == TRUE

initInf:

Object of class "list". Initial values:

`g`	for parameter γ of the gamma distribution of the infectious time
`g.gamma`	for the parameter gamma of the distribution of g
`g.delta`	for the parameter delta of the distribution of g
`d`	for parameter δ of the gamma distribution of the infectious time
`d.gamma`	for the parameter gamma of the distribution of d
`d.delta`	for the parameter delta of the distribution of d

initDia:

Object of class "list". Initial values:

`g`	for parameter γ of the gamma distribution of the seroconversion time
`g.gamma`	for the parameter gamma of the distribution of g
`g.delta`	for the parameter delta of the distribution of g
`d`	for parameter δ of the gamma distribution of the seroconversion time
`d.gamma`	for the parameter gamma of the distribution of d
`d.delta`	for the parameter delta of the distribution of d

Class "LBOptions", directly.

algo: signature(object = "LBOptionsMCMC"):
returns value of slot algo
algo<-: signature(object = "LBOptionsMCMC", value = "vector"):
assigns value to slot algo
LBOptions: signature(object = "LBOptionsMCMC"):
returns values of real option slots (as there are seed, LBModel, ignoreData, algo, randomWalk )
LBOptions<-: signature(object = "LBOptionsMCMC", value = "list"):
assigns value to real option slots (as there are seed, LBModel, ignoreData, algo, randomWalk )
optionsAsDataFrame: signature(object = "LBOptionsMCMC"):
returns real option values in a dataframe format
randomWalk: signature(object = "LBOptionsMCMC"):
returns value of slot randomWalk
randomWalk<-: signature(object = "LBOptionsMCMC", value = "vector" ):
assigns value to slot randomWalk
show: signature(object = "LBOptionsMCMC"):
shows the object
summary: signature(object = "LBOptionsMCMC"):
gives a summary of the object (at the moment no difference to show )
writeOptionFile: signature(object = "LBOptionsMCMC", filename="vector"):
writes a file containing all options as input for java

M. Hoehle and U. Feldmann

See also LBOptions-class and LBOptionsML-class

  opts <- new( "LBOptionsMCMC", algo=c( samples=2500, thin=25, burnin=50000 ),
                                randomWalk=c( "betaRWsigma"= 0.1,
                                              "betaNRWsigma"=0.1,
                                              "gammaERWsigma"=3,
                                              "deltaERWsigma"=1,
                                              "gammaIRWsigma"=1,
                                              "deltaIRWsigma"=1,
                                              "gammaDRWsigma"=3,
                                              "deltaDRWsigma"=1,
                                              "ERWsigma"=6 ),  
                                seed=2003,
                                LBmodel=c( "gamma", "gamma", "gamma", FALSE ),
                                ignoreData=c( TRUE, FALSE, TRUE ),
                                initBeta=list( 0.4, 0.001, 0.001 ),
                                initBetaN=list( init=0.005, gamma=0.001, delta=0.001 ),
                                initIncu=list( g=1, g.gamma=0.001, g.delta=0.001,
                                               d=0.11, d.gamma=0.001, d.delta=0.001 ),
                                initInf=list( 1, 0.001, 0.001, 0.11, 0.001, 0.001 ),
                                initDia=list( 8, 0.001, 0.001, 0.8, 0.001, 0.001 ) )