RMark (version 2.1.1)

TransitionMatrix: Creates a transition matrix of movement parameters for a multi-state(strata) model

Description

Computes all Psi values for a multi-strata mark model and constructs a transition matrix. Standard errors and confidence intervals can also be obtained.

Usage

TransitionMatrix(x, vcv.real = NULL)

Arguments

x

Estimate table from get.real with a single record for each possible transition

vcv.real

optional variance-covariance matrix from the call to get.real

Value

• Either a transition matrix (vcv.real=NULL) or a list of matrices (vcv.real specified) named TransitionMat (transition matrix), se.TransitionMat (se of each transition), lcl.TransitionMat (lower confidence interval limit for each transition), and ucl.TransitionMat (upper confidence interval limit for each transition).

See Also

get.real

Examples

# fit the sequence of multistrata models as shown for ?mstrata
data(mstrata)
run.mstrata=function()
{
#
# Process data
#
mstrata.processed=process.data(mstrata,model="Multistrata")
#
# Create default design data
#
mstrata.ddl=make.design.data(mstrata.processed)
#
#  Define range of models for S; note that the betas will differ from the output
#  in MARK for the ~stratum = S(s) because the design matrix is defined using
#  treatment contrasts for factors so the intercept is stratum A and the other
#  two estimates represent the amount that survival for B abd C differ from A.
#  You can use force the approach used in MARK with the formula ~-1+stratum which
#  creates 3 separate Betas - one for A,B and C.
#
S.stratum=list(formula=~stratum)
S.stratumxtime=list(formula=~stratum*time)
#
#  Define range of models for p
#
p.stratum=list(formula=~stratum)
#
#  Define range of models for Psi; what is denoted as s for Psi
#  in the Mark example for Psi is accomplished by -1+stratum:tostratum which
#  nests tostratum within stratum.  Likewise, to get s*t as noted in MARK you
#  want ~-1+stratum:tostratum:time with time nested in tostratum nested in
#  stratum.
#
Psi.s=list(formula=~-1+stratum:tostratum)
Psi.sxtime=list(formula=~-1+stratum:tostratum:time)
#
# Create model list and run assortment of models
#
model.list=create.model.list("Multistrata")
#
# Add on specific models that are paired with fixed p's to remove confounding
#
p.stratumxtime=list(formula=~stratum*time)
p.stratumxtime.fixed=list(formula=~stratum*time,fixed=list(time=4,value=1))
model.list=rbind(model.list,c(S="S.stratumxtime",p="p.stratumxtime.fixed",
               Psi="Psi.sxtime"))
model.list=rbind(model.list,c(S="S.stratum",p="p.stratumxtime",Psi="Psi.s"))
#
# Run the list of models
#
mstrata.results=mark.wrapper(model.list,data=mstrata.processed,ddl=mstrata.ddl)
#
# Return model table and list of models
#
return(mstrata.results)
}
mstrata.results=run.mstrata()
mstrata.results
# for the best model, get.real to get a list containing all Psi estimates
#  and the v-c matrix
Psilist=get.real(mstrata.results[[1]],"Psi",vcv=TRUE)
Psivalues=Psilist$estimates
# call Transition matrix using values from time==1; the call to the function
# must only contain one record for each possible transition. An error message is
# given if not the case
TransitionMatrix(Psivalues[Psivalues$time==1,])
# call it again but specify the vc matrix to get se and conf interval
TransitionMatrix(Psivalues[Psivalues$time==1,],vcv.real=Psilist$vcv.real)