spillover-tva: address CI codex R11 P3 — §7 Wave E.2 vs follow-up

R11 noted that §7's survey-weights bullet conflated Wave E.2
(cross-sectional Conley + survey via stratified-Conley sandwich on
PSU totals) with the Wave E.2 follow-up (panel-block spatial + serial
Bartlett HAC; requires an effective PSU on the survey design — either
explicit `survey_design.psu=` or `cluster=<col>` injected per the
Wave E.1 warn-and-use-PSU pattern).

Rewrites the bullet to distinguish:
- `conley_lag_cutoff=0`: Wave E.2 stratified-Conley sandwich on PSU
  totals (cross-sectional, spatial only)
- `conley_lag_cutoff>0`: Wave E.2 follow-up panel-block extension
  (library synthesis with within-PSU serial Bartlett HAC, requires
  effective PSU on the survey design)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Author: igerber

docs/tutorials/23_spillover_tva.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "d988694a",
+   "id": "a5f3d36b",
    "metadata": {},
    "source": [
     "# Spillover-aware DiD with `SpilloverDiD` \u2014 a TVA-style worked example\n",
@@ -47,7 +47,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "64ba6796",
+   "id": "a16e76a4",
    "metadata": {},
    "source": [
     "## 2. The synthetic panel\n",
@@ -75,7 +75,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "3ec42967",
+   "id": "1712f2bb",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -157,7 +157,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "ba60f66a",
+   "id": "21aa12c0",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -180,7 +180,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "dd90daa6",
+   "id": "8be4e7c9",
    "metadata": {},
    "source": [
     "## 3. The naive headline \u2014 multi-period TWFE on the full sample\n",
@@ -194,7 +194,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "75f3aa8f",
+   "id": "0c563f94",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -224,7 +224,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "785586b4",
+   "id": "7253fe4c",
    "metadata": {},
    "source": [
     "The naive estimate is roughly **-4.29**, about 58% of the true\n",
@@ -241,7 +241,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "dae0914e",
+   "id": "cb77d87a",
    "metadata": {},
    "source": [
     "## 4. Choosing the spillover bandwidth\n",
@@ -267,7 +267,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "7dba9225",
+   "id": "4804334d",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -294,7 +294,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "2e15f7f6",
+   "id": "787428d1",
    "metadata": {},
    "source": [
     "At `d_bar = 50` km the ring is too narrow: near-controls in the\n",
@@ -330,7 +330,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "44736532",
+   "id": "ce1cb17e",
    "metadata": {},
    "source": [
     "## 5. Fit `SpilloverDiD` and interpret\n",
@@ -342,7 +342,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "1e76fde8",
+   "id": "4558bcfe",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -369,7 +369,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "4ab80644",
+   "id": "e28652ea",
    "metadata": {},
    "source": [
     "With the spillover term in the regression, `SpilloverDiD` cleanly\n",
@@ -387,7 +387,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "c6e4b008",
+   "id": "2e005043",
    "metadata": {},
    "source": [
     "## 6. Robust inference with Conley spatial-HAC\n",
@@ -411,7 +411,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "7425c521",
+   "id": "25d20f8c",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -445,7 +445,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "d739826c",
+   "id": "e6d5ee1b",
    "metadata": {},
    "source": [
     "Point estimates are identical across all three rows \u2014 the variance\n",
@@ -500,7 +500,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "c86340f2",
+   "id": "5cc89608",
    "metadata": {},
    "source": [
     "## 7. Practitioner takeaways and where to go next\n",
@@ -540,9 +540,16 @@
     "  `tutorials/12_two_stage_did.ipynb` for the TwoStageDiD event-study\n",
     "  pattern this mirrors).\n",
     "- *Survey weights* \u2014 `survey_design=SurveyDesign(...)` supports\n",
-    "  H\u00e1jek-weighted point estimates with Binder TSL variance, including\n",
-    "  combined `survey_design + vcov_type=\"conley\"` panel-block sandwich\n",
-    "  (Wave E.2). A dedicated survey-design tutorial is on the roadmap.\n",
+    "  H\u00e1jek-weighted point estimates with Binder TSL variance. Combined\n",
+    "  with `vcov_type=\"conley\"` and `conley_lag_cutoff=0` (cross-\n",
+    "  sectional spatial only) this is the Wave E.2 stratified-Conley\n",
+    "  sandwich on PSU totals. The panel-block extension\n",
+    "  `conley_lag_cutoff > 0` (spatial + within-PSU serial Bartlett HAC)\n",
+    "  is the Wave E.2 follow-up library synthesis, and it requires an\n",
+    "  effective PSU on the survey design (either explicit\n",
+    "  `survey_design.psu=` or `cluster=<col>` injected per Wave E.1's\n",
+    "  warn-and-use-PSU pattern). A dedicated `SpilloverDiD`\n",
+    "  survey-design tutorial is on the roadmap.\n",
     "\n",
     "**References:**\n",
     "- Butts, K. (2021). *Difference-in-Differences with Spatial\n",