Fix: Clarify base_period interaction with anticipation in Tutorial 02

Updated 3 locations to correctly document that base_period="universal"
uses g-anticipation-1 (not just g-1) when anticipation > 0:
- Markdown explanation of base_period options
- Code comment in comparison example
- Print statement output

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

Author: igerber

docs/tutorials/02_staggered_did.ipynb

@@ -467,7 +467,7 @@
     "\n",
     "The `base_period` parameter controls how the reference period is selected:\n",
     "- `\"varying\"` (default): For pre-treatment periods, compares t to t-1 (consecutive comparisons)\n",
-    "- `\"universal\"`: Always compares to g-1 (the period just before treatment)\n",
+    "- `\"universal\"`: Always compares to g-1 (or g-anticipation-1 when anticipation > 0)\n",
     "\n",
     "Both produce identical post-treatment effects; they differ only for pre-treatment diagnostics."
    ]
@@ -545,7 +545,7 @@
     "# Compare varying vs universal base period\n",
     "cs_universal = CallawaySantAnna(\n",
     "    control_group=\"never_treated\",\n",
-    "    base_period=\"universal\"  # Always use g-1 as base\n",
+    "    base_period=\"universal\"  # Always use g-1 as base (g-anticipation-1 if anticipation > 0)\n",
     ")\n",
     "\n",
     "results_universal = cs_universal.fit(\n",
@@ -570,7 +570,7 @@
     "        print(f\"{event_time:>12} {varying_eff:>12.4f} {universal_eff:>12.4f} {diff:>12.4f}\")\n",
     "\n",
     "print(\"\\nNote: 'Varying' uses consecutive period comparisons (t vs t-1)\")\n",
-    "print(\"      'Universal' compares all periods to g-1\")"
+    "print(\"      'Universal' compares all periods to g-1 (g-anticipation-1 if anticipation > 0)\")"
    ]
   },
   {