Type: Package
Title: Imputation Estimator from Borusyak, Jaravel, and Spiess (2021)
Version: 0.5.0
Description: Estimates Two-way Fixed Effects difference-in-differences/event-study models using the imputation-based approach proposed by Borusyak, Jaravel, and Spiess (2021).
Encoding: UTF-8
LazyData: true
RoxygenNote: 7.3.2
Depends: R (≥ 4.1.0), fixest (≥ 0.13.2), data.table (≥ 1.10.0)
Imports: Matrix
Suggests: haven, testthat (≥ 3.0.0)
Config/testthat/edition: 3
URL: https://github.com/kylebutts/didimputation
License: MIT + file LICENSE
NeedsCompilation: no
Packaged: 2025-12-15 15:21:11 UTC; kbutts
Author: Kyle Butts ORCID iD [aut, cre]
Maintainer: Kyle Butts <buttskyle96@gmail.com>
Repository: CRAN
Date/Publication: 2025-12-17 06:40:41 UTC

Simulated data with two treatment groups and heterogenous effects

Description

Generated using the following call: did2s::gen_data(panel = c(1990, 2020), g1 = 2000, g2 = 2010, g3 = 0, te1 = 2, te2 = 1, te3 = 0, te_m1 = 0.05, te_m2 = 0.15, te_m3 = 0)

Usage

df_het

Format

A data frame with 31000 rows and 15 variables:

unit

individual in panel data

year

time in panel data

g

the year that treatment starts

dep_var

outcome variable

treat

T/F variable for when treatment is on

rel_year

year relative to treatment start. Inf = never treated.

rel_year_binned

year relative to treatment start, but <=-6 and >=6 are binned.

unit_fe

Unit FE

year_fe

Year FE

error

Random error component

te

Static treatment effect = te

te_dynamic

Dynamic treatmet effect = te_m

state

State that unit is in

group

String name for group

Simulated data with two treatment groups and homogenous effects

Description

Generated using the following call: did2s::gen_data(panel = c(1990, 2020), g1 = 2000, g2 = 2010, g3 = 0, te1 = 2, te2 = 2, te3 = 0, te_m1 = 0, te_m2 = 0, te_m3 = 0)

Usage

df_hom

Format

A data frame with 31000 rows and 15 variables:

unit

individual in panel data

year

time in panel data

g

the year that treatment starts

dep_var

outcome variable

treat

T/F variable for when treatment is on

rel_year

year relative to treatment start. Inf = never treated.

rel_year_binned

year relative to treatment start, but <=-6 and >=6 are binned.

unit_fe

Unit FE

year_fe

Year FE

error

Random error component

te

Static treatment effect = te

te_dynamic

Dynamic treatmet effect = te_m

group

String name for group

state

State that unit is in

weight

Weight from runif()

Borusyak, Jaravel, and Spiess (2021) Estimator

Description

Treatment effect estimation and pre-trend testing in staggered adoption diff-in-diff designs with an imputation approach of Borusyak, Jaravel, and Spiess (2021)

Usage

did_imputation(
  data,
  yname,
  gname,
  tname,
  idname,
  first_stage = NULL,
  wname = NULL,
  wtr = NULL,
  horizon = NULL,
  pretrends = NULL,
  cluster_var = NULL
)

Arguments

data

A data.frame

yname

String. Variable name for outcome. Use fixest c() syntax for multiple lhs, e.g. "c(y1, y2)".

gname

String. Variable name for unit-specific date of treatment (never-treated should be zero or NA).

tname

String. Variable name for calendar period.

idname

String. Variable name for unique unit id.

first_stage

Formula for Y(0). Formula following fixest::feols. Fixed effects specified after "|". If not specified, then just unit and time fixed effects will be used.

wname

String. Variable name for estimation weights of observations. This is used in estimating Y(0) and also augments treatment effect weights.

wtr

Character vector of treatment weight names (see horizon for standard static and event-study weights)

horizon

Integer vector of event_time or TRUE. This only applies if wtr is left as NULL. if specified, weighted averages/sums of treatment effects will be reported for each of these horizons separately (i.e. tau0 for the treatment period, tau1 for one period after treatment, etc.). If TRUE, all horizons are used. If wtr and horizon are null, then the static treatment effect is calculated.

pretrends

Integer vector or TRUE. Which pretrends to estimate. If TRUE, all pretrends are used.

cluster_var

String. Variable name for clustering groups. If not supplied, then idname is used as default.

Details

The imputation-based estimator is a method of calculating treatment effects in a difference-in-differences framework. The method estimates a model for Y(0) using untreated/not-yet-treated observations and predicts Y(0) for the treated observations hat(Y_it(0)). The difference between treated and predicted untreated outcomes Y_it(1) - hat(Y_it(0)) serves as an estimate for the treatment effect for unit i in period t. These are then averaged to form average treatment effects for groups of (i, t).

Value

A data.frame containing treatment effect term, estimate, standard error and confidence interval. This is in tidy format.

Examples

Load example dataset which has two treatment groups and homogeneous treatment effects 

# Load Example Dataset
data("df_hom", package="didimputation")

Static TWFE

You can run a static TWFE fixed effect model for a simple treatment indicator 

did_imputation(data = df_hom, yname = "dep_var", gname = "g",
               tname = "year", idname = "unit")
#>      term estimate  std.error conf.low conf.high
#>    <char>    <num>      <num>    <num>     <num>
#> 1:  treat 2.024639 0.03243596 1.961065  2.088214

Event Study

Or you can use relative-treatment indicators to estimate an event study estimate 

did_imputation(data = df_hom, yname = "dep_var", gname = "g",
               tname = "year", idname = "unit", horizon=TRUE)
#>       term estimate  std.error conf.low conf.high
#>     <char>    <num>      <num>    <num>     <num>
#>  1:      0 2.117232 0.07368419 1.972811  2.261653
#>  2:      1 1.856536 0.07672104 1.706163  2.006909
#>  3:      2 1.986357 0.07137180 1.846468  2.126246
#>  4:      3 2.004843 0.07653409 1.854836  2.154850
#>  5:      4 1.950228 0.07543636 1.802372  2.098083
#>  6:      5 2.038302 0.07580288 1.889728  2.186875
#>  7:      6 2.031571 0.07223098 1.889999  2.173144
#>  8:      7 2.025286 0.07541719 1.877468  2.173104
#>  9:      8 1.976081 0.07493409 1.829210  2.122951
#> 10:      9 2.121434 0.07268404 1.978974  2.263895
#> 11:     10 2.087984 0.08271442 1.925864  2.250105
#> 12:     11 1.942825 0.11421421 1.718965  2.166685
#> 13:     12 1.940532 0.11200348 1.721005  2.160059
#> 14:     13 1.964569 0.11361969 1.741875  2.187264
#> 15:     14 2.023456 0.11753255 1.793092  2.253820
#> 16:     15 2.235051 0.12110086 1.997693  2.472409
#> 17:     16 2.178438 0.11552325 1.952013  2.404864
#> 18:     17 1.935576 0.11278311 1.714521  2.156631
#> 19:     18 2.134953 0.10993120 1.919488  2.350418
#> 20:     19 2.111984 0.11146282 1.893517  2.330451
#> 21:     20 1.925168 0.11214206 1.705370  2.144967
#>       term estimate  std.error conf.low conf.high

Example from Cheng and Hoekstra (2013)

Here's an example using data from Cheng and Hoekstra (2013) 

# Castle Data
castle = haven::read_dta("https://github.com/scunning1975/mixtape/raw/master/castle.dta")

did_imputation(data = castle, yname = "c(l_homicide, l_assault)", gname = "effyear",
              first_stage = ~ 0 | sid + year,
              tname = "year", idname = "sid")
#> Key: <lhs>
#>           lhs   term   estimate  std.error    conf.low conf.high
#>        <char> <char>      <num>      <num>       <num>     <num>
#> 1:  l_assault  treat 0.04955260 0.05132258 -0.05103966 0.1501449
#> 2: l_homicide  treat 0.07980155 0.06088398 -0.03953105 0.1991341