VBJM_fit {VBJM}

The function to fit VBJM.

Description

The function is used to fit joint models using variational inference algorithm.

Usage

VBJM_fit(
  LongData = NULL,
  SurvData = NULL,
  marker.name = NULL,
  control_list = NULL,
  maxiter = 100,
  eps = 1e-04
)

Arguments

LongData

a data frame containing the longitudinal data (see LongData).

SurvData

a data frame containing the survival data (see SurvData).

marker.name

a vector indicating which set of longitudinal biomarkers to be analyzed. If NULL, all biomarkers in LongData will be used.

control_list

a list of parameters specifying the joint model (see control_list).

maxiter

the maximum number of iterations.

eps

threshold for convergence.

Value

return a data frame with estimates, standard errors, and 95% CIs for each of the following parameters, where VAR indicates the corresponding variable name.

VAR_alpha

the parameters for the effects of biomarkers in the survival submodel, where VAR indicates the names for the biomarkers.

Weibull_shape

the shape parameter in the Weibull baseline hazard in the survival submodel.

Weibull_scale

the scale parameter in the Weibull baseline hazard in the survival submodel.

Surv_gamma_VAR

the parameters for the effects of baseline covariates in the survival submodel.

VAR_fix

the parameters for the fixed-effects in the longitudinal submodel.

References

Jieqi Tu and Jiehuan Sun (2023). "Gaussian variational approximate inference for joint models of longitudinal biomarkers and a survival outcome". Statistics in Medicine, 42(3), 316-330.

Examples

data(VBJMdata)
flex_time_fun <- function(x=NULL){
    xx = matrix(x, ncol = 1)
    colnames(xx) = c("year_l")
    xx
}
ran_time_ind = 1 ## random time-trend effects
control_list = list(
  ID_name = "ID", item_name = "item",
  value_name = "value",  time_name = "years",
  fix_cov = NULL, random_cov = NULL,
  FUN = flex_time_fun, ran_time_ind=ran_time_ind,
  surv_time_name = "ftime",  surv_status_name = "fstat",
  surv_cov = "x", n_points = 5
)

## takes about one minute.
res = VBJM_fit(LongData=LongData, SurvData=SurvData,
               control_list=control_list)