mle.fun
, mle.ar1.fun
,
mle.a3.fun
, mle.ar1.non3
or lmeNB
.
This function computes the probability of observing the response counts as large as those new observations of subject i y_i,new=(y_i,m_i+1,...,y_i,ni) conditional on the subject's previous observations y_i,pre(y_i,1,...,y_i,m_i).That is, this function returns a point estimate and its asymptotic 95
Pr(q(Y_i,new)>=q(y_i,new)| Y_i,pre=y_i,pre).The standard error is not produced when the semi-parametric approach is employed.A scalar statistic to summarize the new response counts can be either the total count, q(Y_i,new)=sum_{j=m_i+1}^ni Y_ij, or the maximum, q(Y_i,new)=max { Y_ij;j=m_i+1,...,n_i }.See Zhao et al., for more details.
index.batch(data,labelnp, ID, Vcode,olmeNB,subset=NULL,
qfun = "sum", IPRT = TRUE, i.se = TRUE, iMC = FALSE)
TRUE
.
For examples, if patient i has a n_i repeated measures and the last n_i-m_i+1 measures are new, then
then lab
c(rep(1,n_1),rep(2,n_2),...,rep(N,n_N))
mle.fun
,mle.ar1.fun
,mle.a3.fun
,mle.ar1.non3<
qfun="sum"
,
a scalar statistic to summarize the new response counts is the total count.
If qfun="max"
,
a scalar statistic to summarize the new response counts is the maximum.i.se=TRUE
then the standard errors of the estimator of the conditional probability are returned for the output of
mle.fun
or mle.ar1.fun
mle.ar1.fun
and mle.ar1.non3
.
If iMC=TRUE
then the function MCCP.ar1
is called and the lmeNB
The functions to fit the relevant models:
mle.fun
,
mle.ar1.fun
,
mle.a3.fun
,
mle.ar1.non3
,The subroutines of index.batch
:
jCP.ar1
,
CP1.ar1
,
MCCP.ar1
,
CP.ar1.se
,
CP.se
,
jCP
,
The functions to generate simulated datasets:
rNBME.R
.
## See the examples in linked R-functions.
Run the code above in your browser using DataLab