Address PR #97 review round 6: clarify ATT(g,t) equation documentation

Add notes explaining that the canonical ATT(g,t) equation (using g-1 as base)
applies to post-treatment effects and base_period="universal". With
base_period="varying" (default), pre-treatment uses t-1 for consecutive
comparisons useful in parallel trends diagnostics.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Author: igerber

diff_diff/staggered.py

@@ -282,6 +282,9 @@ class CallawaySantAnna(
         E[Y(0)_t - Y(0)_g-1 | G=g] = E[Y(0)_t - Y(0)_g-1 | C=1]
 
     where G=g indicates treatment cohort g and C=1 indicates control units.
+    This uses g-1 as the base period, which applies to post-treatment (t >= g).
+    With base_period="varying" (default), pre-treatment uses t-1 as base for
+    consecutive comparisons useful in parallel trends diagnostics.
 
     References
     ----------

docs/methodology/REGISTRY.md

@@ -181,6 +181,8 @@ ATT(g,t) = E[Y_t - Y_{g-1} | G_g=1] - E[Y_t - Y_{g-1} | C=1]
 ```
 where G_g=1 indicates units first treated in period g, and C=1 indicates never-treated.
 
+*Note:* This equation uses g-1 as the base period, which applies to post-treatment effects (t ≥ g) and `base_period="universal"`. With `base_period="varying"` (default), pre-treatment effects use t-1 as base for consecutive comparisons (see Base period selection in Edge cases).
+
 With covariates (doubly robust):
 ```
 ATT(g,t) = E[((G_g - p̂_g(X))/(1-p̂_g(X))) × (Y_t - Y_{g-1} - m̂_{0,g,t}(X) + m̂_{0,g,g-1}(X))] / E[G_g]