DIDmultiplegt (version 2.1.0)

did_multiplegt_old: Old DID Multiplegt Estimator (de Chaisemartin and D'Haultfoeuille 2020)

Description

This is the old version of did_multiplegt from de Chaisemartin and D'Haultfoeuille (2020). For most use cases, we recommend using did_multiplegt with mode="dyn" instead, which is faster and has more features.

Usage

did_multiplegt_old(
  df,
  Y,
  G,
  T,
  D,
  controls = c(),
  placebo = 0,
  dynamic = 0,
  threshold_stable_treatment = 0,
  recat_treatment = NULL,
  trends_nonparam = NULL,
  trends_lin = NULL,
  brep = 0,
  cluster = NULL,
  covariance = FALSE,
  average_effect = NULL,
  parallel = FALSE
)

Value

A list with treatment effects and related statistics

Arguments

df

the data frame for input

Y

the name of Y variable

G

the name of group variable

T

the name of time variable

D

the name of treatment variable

controls

the list of names of control variables, empty if not specified

placebo

the number of placebo estimators

dynamic

the number of dynamic estimators

threshold_stable_treatment

the threshold to mark a difference stable

recat_treatment

the name of treatment group recategorized

trends_nonparam

trends nonparametric option

trends_lin

trends linear option

brep

the number of bootstrap replications

cluster

cluster variable for standard errors

covariance

whether to compute covariance

average_effect

average effect option

parallel

whether to run bootstrap in parallel