boot function

Parametric bootstrap

Parametric bootstrap for bivariate normally distributed data

CAMANboot(obs1, obs2, var1, var2, lambda11, lambda12, 
     prob1, lambda21, lambda22, prob2, rep, 
     data,numiter=10000,acc=1.e-7)

Arguments

• obs1: the first column of the observations

• obs2: the second column of the observations

• data: a data frame

• var1: Variance of the first column of the observations(except meta-analysis)

• var2: Variance of the second column of the observations (except meta-analysis)

• lambda11: first means of the first column of the observations

• lambda12: first means of the second column of the observations

• prob1: first mixing weight

• lambda21: second means of the first column of the observations

• lambda22: second means of the second column of the observations

• prob2: second mixing weight

• numiter: parameter to control the maximal number of iterations in the VEM and EM loops. Default is 5000.

• acc: convergence criterion. Default is 1.e-7

• rep: number of repetitions

Examples

 for bivariate normally distributed data
data(CT)
library(mvtnorm)
hom1<-c(3.142442)
hom2<-c(-1.842393)
p1<-c(1)
start1<-c(2.961984,3.226141)
start2<-c(-2.578836, -1.500823)
pvem<-c(0.317,0.683)
CAMANboot(obs1=logitTPR, obs2=logitTNR, var1=varlogitTPR, var2=varlogitTNR,
          lambda11=hom1, lambda12=hom2, prob1=p1, 
          lambda21=start1, lambda22=start2, prob2=pvem,rep=3,data=CT)