estimate_ATE_RIRC: Estimate the ATE using Random-Intercept, Constant-Coefficient...

In lmiratrix/blkvar: ATE and Treatment Variation Estimation for Blocked and Multisite RCTs

Estimate the ATE using Random-Intercept, Constant-Coefficient (RICC) Model.

Description

This model has a single treatment coefficient, and a random intercept for the site control average. So it is analogous to a fixed effect model, but with a random effect.

Usage

estimate_ATE_RICC(Yobs, Z, B, data = NULL, REML = TRUE, control_formula = NULL)

estimate_ATE_RIRC(
  Yobs,
  Z,
  B,
  data = NULL,
  include_testing = FALSE,
  REML = !include_testing,
  keep_EB_estimates = TRUE,
  pool = FALSE,
  control_formula = NULL
)

Arguments

Yobs	Name of outcome variable (assumed to exist in data)
Z	vector of assignment indicators (1==treated)
B	Name of the block indicator.
data	Dataframe with all needed variables.
REML	Logical, Restricted maximum likelihood or maximum likelihood estimation. Default of TRUE if include_testing = FALSE and FALSE otherwise. Note that FIRC can fail badly in estimating cross-site variation when REML=FALSE.
control_formula	The control_formula argument must be of the form ~ X1 + X2 + ... + XN. (nothing on left hand side of ~)
include_testing	Logical Include likelihood ratio test for cross-site treatment variation.
keep_EB_estimates	TRUE means returned object has EB estimates. FALSE means do not keep them.
pool	TRUE means tx and co have same reBual variance. FALSE gives seperate estimates for each (recommended, default).

Details

There is no test for cross site variation for this method, since we assume none.

lmiratrix/blkvar documentation built on Nov. 18, 2024, 1:27 p.m.