nonlinear_attgt: Nonlinear Staggered DiD: Group-Time ATT Estimation

In NonlinearDiD: Staggered Difference-in-Differences with Nonlinear Outcomes

Nonlinear Staggered DiD: Group-Time ATT Estimation

Description

Computes group-time average treatment effects on the treated (ATT(g,t)) for staggered difference-in-differences designs with nonlinear outcomes.

This function extends Callaway & Sant'Anna (2021) to handle binary, count, and other nonlinear outcomes where the standard linear parallel trends assumption is misspecified. The key methodological contributions are:

1. Parallel trends on the latent index (for logit/probit): Instead of assuming parallel trends in E[Y], we assume parallel trends in the latent utility F^{-1}(E[Y]).

2. Doubly-robust nonlinear estimator: Combines outcome regression (nonlinear model) with propensity score weighting, inheriting DR properties in the nonlinear setting.

3. Odds-ratio DiD: A scale-free estimand appropriate for binary outcomes that does not require parallel trends in probabilities.

4. Nonparametric bounds: When no functional form is assumed, provides sharp bounds on ATT(g,t).

Usage

nonlinear_attgt(
  data,
  yname,
  tname,
  idname,
  gname,
  xformla = ~1,
  outcome_model = c("logit", "probit", "poisson", "negbin", "linear"),
  estimand = c("att", "odds_ratio", "ape"),
  control_group = c("nevertreated", "notyetreated"),
  doubly_robust = TRUE,
  boot = FALSE,
  nboot = 999,
  boot_type = c("multiplier", "empirical"),
  alpha = 0.05,
  parallel = FALSE,
  pl_cores = 2L,
  anticipation = 0L
)

Arguments

data	A data frame in long format (one row per unit-period).
yname	Character. Name of the outcome variable column.
tname	Character. Name of the time period column.
idname	Character. Name of the unit identifier column.
gname	Character. Name of the treatment cohort column (the period when a unit first receives treatment; 0 or Inf for never-treated units).
xformla	A one-sided formula for covariates (e.g., ~ x1 + x2). Default is ~ 1 (intercept only).
outcome_model	Character. The outcome model to use. One of: "logit": Logistic regression (for binary Y) "probit": Probit regression (for binary Y) "poisson": Poisson regression (for count Y) "negbin": Negative binomial (for overdispersed count Y) "linear": Linear model (reproduces CS2021 when combined with doubly_robust = TRUE)
estimand	Character. The treatment effect estimand: "att": Average treatment effect on the treated (default) "odds_ratio": Odds ratio DiD (binary outcomes only) "ape": Average partial effect on the probability scale
control_group	Character. Which units serve as the control group: "nevertreated": Use never-treated units only (default) "notyetreated": Use not-yet-treated units
doubly_robust	Logical. If TRUE (default), uses the doubly-robust estimator that combines propensity score weighting with outcome regression. More robust to model misspecification.
boot	Logical. If TRUE, uses bootstrap for inference. Default FALSE.
nboot	Integer. Number of bootstrap iterations. Default 999.
boot_type	Character. Type of bootstrap: "multiplier" (default, fast) or "empirical".
alpha	Numeric. Significance level for confidence intervals. Default 0.05.
parallel	Logical. Use parallel processing for bootstrap. Default FALSE.
pl_cores	Integer. Number of cores for parallel processing.
anticipation	Integer. Number of periods of anticipation allowed. Default 0.

Value

An object of class nonlinear_attgt containing:

attgt

Data frame of ATT(g,t) estimates, standard errors, and confidence intervals for each (group, time) pair.

call

The matched call.

args

List of arguments used.

boot_draws

Matrix of bootstrap draws (if boot = TRUE).

References

Callaway, B., & Sant'Anna, P. H. C. (2021). Difference-in-differences with multiple time periods. Journal of Econometrics, 225(2), 200-230.

Wooldridge, J. M. (2023). Simple approaches to nonlinear difference-in-differences with panel data. The Econometrics Journal, 26(3).

Roth, J., & Sant'Anna, P. H. C. (2023). When is parallel trends sensitive to functional form? Econometrica, 91(2), 737-747.

Examples

# Simulate binary panel data
set.seed(42)
dat <- sim_binary_panel(n = 500, nperiods = 6, prop_treated = 0.4)

# Estimate ATT(g,t) with logistic outcome model
result <- nonlinear_attgt(
  data = dat,
  yname = "y",
  tname = "period",
  idname = "id",
  gname = "g",
  outcome_model = "logit",
  control_group = "nevertreated"
)

summary(result)
plot(result)

NonlinearDiD documentation built on May 6, 2026, 1:06 a.m.