Merge pull request #184 from igerber/docs/continuous-did-api-reference

Fix ContinuousDiD SE method: influence function, not delta method

Author: igerber

docs/choosing_estimator.rst

@@ -276,8 +276,8 @@ differences helps interpret results and choose appropriate inference.
      - Bootstrap or placebo-based
      - Default uses bootstrap resampling. Set ``n_bootstrap=0`` for placebo-based inference using pre-treatment residuals.
    * - ``ContinuousDiD``
-     - Analytical (default)
-     - Uses delta method SEs by default. Use ``n_bootstrap=199`` (or higher) for multiplier bootstrap inference with proper CIs.
+     - Analytical (influence function)
+     - Uses influence-function-based SEs by default. Use ``n_bootstrap=199`` (or higher) for multiplier bootstrap inference with proper CIs.
 
 **Recommendations by sample size:**
 

docs/methodology/continuous-did.md

@@ -298,7 +298,7 @@ ATT(d) +/- z_{0.975} * sigma_K(d) / sqrt(n)
 ### Summary parameter inference
 
 ACRT^{glob} plug-in estimator is sqrt(n)-consistent and asymptotically normal.
-Standard errors via delta method or bootstrap.
+Standard errors via influence functions or multiplier bootstrap.
 
 ---