Diagnose TWFE-DiD weights (de Chaisemartin & D'Haultfoeuille, 2020)

Thin interface to TwoWayFEWeights::twowayfeweights: returns the decomposition of the two-way fixed-effects DiD estimand into the weighted average of the \(N \times T\) unit-time ATEs. Use this to quantify how many of the implicit comparisons receive negative weight, which is the canonical diagnostic for whether a TWFE specification can be interpreted as a convex combination of treatment effects.

Usage

morie_did_twoway_fe_weights(
  panel,
  group,
  time,
  treatment,
  outcome = NULL,
  type = "feTR",
  ...
)

Arguments

panel: A long-format balanced (or near-balanced) panel data.frame.
group: Name of the unit / group identifier column.
time: Name of the time period column.
treatment: Name of the binary or continuous treatment column.
outcome: Optional outcome column. When supplied, TwoWayFEWeights computes the weights AND the implied TWFE coefficient; when NULL, only the weights are returned (faster, dimension-free).
type: Weight type passed through to TwoWayFEWeights::twowayfeweights: "feTR" (default, feasible TR weights), "feS", "fdTR", or "fdS". See the TwoWayFEWeights documentation.
...: Additional arguments forwarded to TwoWayFEWeights::twowayfeweights.

Value

An S3 list of class morie_did_twfe_diagnostics with elements n_negative_weights, sum_weights, sum_negative_weights, share_negative_weights, method, and raw (the full twowayfeweights object).

Details

Wrapper-as-extender: morie_did_panel_fe already estimates the TWFE coefficient; this function exposes the diagnostic side of the same backend so that downstream MRM analyses can flag heterogeneous- treatment-effects bias without leaving the rmorie API.

References

de Chaisemartin, C., & D'Haultfoeuille, X. (2020). Two-way fixed effects estimators with heterogeneous treatment effects. American Economic Review, 110(9), 2964–2996.