MRStdCRT_point: Model-robust standardization in CRT Point Estimate

Description

This function calculates a model-robust point estimate for a clustered randomized trial (CRT).

Usage

MRStdCRT_point(
  formula,
  data,
  cluster,
  trt,
  trtprob,
  family = gaussian(link = "identity"),
  corstr,
  method = "GLM",
  scale
)

Value

A list with the following components: - `data1`: A data frame containing all individual-level observations. - `data_clus`: A data frame contaning all cluster-level summaries. - `c(cate,iate,test_NICS)`: A vector containing: (i) cate: point estimate for cluster-average treatment effect; (ii) iate: point estimate for individual-average treatment effect; (iii) test_NICS: value of test statistics for non-informative cluster sizes.

Arguments

formula: A formula for the outcome mean model, including covariates.
data: A data frame where categorical variables should already be converted to dummy variables.
cluster: A string representing the column name of the cluster ID in the data frame.
trt: A string representing the column name of the treatment assignment per cluster.
trtprob: A vector of treatment probabilities per cluster (for each individual), conditional on covariates. Default is rep(0.5,nrow(data))
family: The link function for the outcome. Can be one of the following: - `gaussian(link = "identity")`: for continuous outcomes. Default is gaussian("identity") - `binomial(link = "logit")`: for binary outcomes. - `poisson(link = "log")`: for count outcomes. - `gaussian(link = "logit")`: for binary outcomes with logit link to model the genealized linear model.
corstr: A string specifying the correlation structure for GEE models (e.g., "exchangeable", "independence").
method: A string specifying the outcome mean model. Possible values are: - 'GLM': Generalized linear model on cluster-level means (continous/binary outcome). - 'LMM': linear mixed model on individual-level observations (continuous outcome). - 'GEE': marginal models fitted by generalized estimating equations. - 'GLMM': generalized linear mixed model.
scale: A string specifying the risk measure of interest. Can be 'RD' (risk difference), 'RR' (relative risk), or 'OR' (odds ratio).