nonpara_fn: Get bootstrap variance estimate

In Merck/mmrm: Mixed model repeated measures and its extension

Description

For a given dataset, compute the bootstrap variance estimate by a prespecified method

Usage

nonpara_fn(
  formula,
  data_wide = NULL,
  data_long = NULL,
  time_name = NULL,
  id_name,
  trt_name,
  M,
  B,
  fit_model,
  estimator,
  method,
  llh_method = NULL
)

Arguments

formula	a symbolic description of the model to be fitted
data_wide	wide-form of the data frame
data_long	long-form of the data frame
time_name	name of the time variable (needed for long-form data)
id_name	name of the id variable
trt_name	name of the treatment variable
M	imputation size
B	number of bootstrap replicates
fit_model	type of the analysis model. Available: lm, Rfit::rfit (rank regressoin), MASS::rlm (robust regression)
estimator	type of the estimator. Available: sample mean, reg with interaction, reg without interaction
method	several methods to use. Available: naive MI, sequential MI, naive likelihood, sequential likelihood
llh_method	name of the likelihood-based method. Available: PMM, CBMI

Value

variance estimation by nonparametric bootstrap

Merck/mmrm documentation built on Dec. 17, 2021, 4:12 a.m.