fixed_effect_estimators: Fixed effect linear regression

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

Fixed effect linear regression

Description

Fit regressions with block fixed effects (and a single treatment parameter). Calculate standard errors in a variety of ways.

Usage

fixed_effect_estimators(
  Yobs,
  Z,
  B,
  siteID = NULL,
  data = NULL,
  block.stats = NULL,
  control_formula = NULL
)

Arguments

Yobs	Name of outcome variable (assumed to exist in data)
Z	vector of assignment indicators (1==treated)
B	block ids
siteID	If not null, name of siteID that has randomization blocks
data	Dataframe of the data to analyse.
block.stats	Table of precomputed block-level statistics (optional, for speed concerns; this gets precomputed in compare_methods).
control_formula	The control_formula argument must be of the form ~ X1 + X2 + ... + XN. (nothing on left hand side of ~)

Details

For the club sandwich estimation ("Club"), see code proposed at https://www.jepusto.com/handmade-clubsandwich/

Value

Dataframe of results for different estimators.

See Also

Other linear model estimators: interacted_linear_estimators(), linear_model_estimators(), weighted_linear_estimators()

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