Synthetic DiD via synthdid::synthdid_estimate (explicit-name API)

Parallel to morie_did_synthetic, this is the explicit-name wrapper that surfaces the full synthdid estimator and its placebo / jackknife variance pieces. Use this when you want to pass through additional synthdid arguments or inspect the unit / time weights side-by-side; use morie_did_synthetic when you want the rmorie result-list shape consumed by morie_did_* downstream code.

Usage

morie_did_synthdid_estimate(
  panel,
  unit,
  time,
  treatment,
  outcome,
  vcov_method = "placebo",
  ...
)

Arguments

panel

Long-format balanced panel.

unit

Unit identifier column.

time

Time period column.

treatment

Binary treatment indicator that turns on at onset for treated units and is zero everywhere for controls (the synthdid W convention).

outcome

Outcome column.

vcov_method

Variance estimator passed to stats::vcov.synthdid_estimate: one of "placebo" (default), "bootstrap", "jackknife".

...

Additional arguments forwarded to synthdid::synthdid_estimate (e.g. zeta, omega.intercept).

Value

An S3 list of class morie_did_synthdid_result with elements att, std_error, vcov_method, n_treated, n_control, n_pre, n_post, method, and raw (the full synthdid_estimate object).

Details

Wrapper-as-extender: rmorie already wraps synthdid once via morie_did_synthetic; this entry point gives MRM / paper callers the canonical Arkhangelsky et al. (2021) API with a morie_* name so they don't need to load synthdid directly.

References

Arkhangelsky, D., Athey, S., Hirshberg, D. A., Imbens, G. W., & Wager, S. (2021). Synthetic difference-in-differences. American Economic Review, 111(12), 4088–4118.

See also

morie_did_synthetic.