# Full-empirical-analysis-skill-Stata

> Classical end-to-end empirical analysis workflow in the traditional Stata ecosystem — native Stata + reghdfe + ivreg2 + csdid + did_imputation + eventstudyinteract + sdid + rdrobust + rddensity + synth + synth_runner + psmatch2 + teffects + ebalance + coefplot + esttab + asdoc + binscatter. **Defaults to economics empirical-paper style** (AER / QJE / AEJ) — every run produces a publication-ready output set with a multi-column regression table (M1→M6 progressive controls/FE) as the centerpiece, plus Table 1 (descriptives), mechanism / heterogeneity / robustness tables, and event-study + coefficient + trend figures. Covers the full 8-step Stata pipeline an applied economist runs on every paper — (1) data import & cleaning (use/import, destring, misstable, duplicates, merge assert), (2) variable construction (gen/egen/winsor2/xtile/xtset with L./F./D.), (3) descriptive statistics & Table 1 (tabstat/balancetable/asdoc), (4) classical diagnostic tests (sktest/swilk/hettest/imtest/xtserial/xttest3/vif/dfuller/kpss/

- Skill: `brycewang-stanford/full-empirical-analysis-skill-stata` (Agent Skill, multi-file: 10 files)
- Install (CLI): `npx skillmds add brycewang-stanford/full-empirical-analysis-skill-stata`
- Raw SKILL.md: https://api.skillmd.com/api/skills/brycewang-stanford/full-empirical-analysis-skill-stata/raw
- Safety review: pending (external: skill-scanner PASS, skillspector WARNING)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: DevOps & Infra
- Author: brycewang-stanford (https://skillmd.com/u/brycewang-stanford)
- Updated: 2026-08-19
- Page: https://skillmd.com/skills/brycewang-stanford/full-empirical-analysis-skill-stata

---


# Full Empirical Analysis — Classical Stata Workflow

This skill is the *canonical* 8-step pipeline an applied economist runs on every empirical paper, written in the **traditional Stata ecosystem** — native Stata + the 20+ community commands that have become de-facto standards (`reghdfe`, `ivreg2`, `csdid`, `did_imputation`, `eventstudyinteract`, `sdid`, `rdrobust`, `rddensity`, `synth`, `synth_runner`, `psmatch2`, `teffects`, `ebalance`, `coefplot`, `esttab`, `outreg2`, `boottest`, `ritest`, `rwolf`, `bacondecomp`, `honestdid`, `binscatter`).

**Companion skills**: if the user wants the same pipeline in Python, route to `00-StatsPAI_skill` (agent-native DSL) or `00.1-Full-empirical-analysis-skill` (explicit Python stack). **This skill is the Stata counterpart** — every step produces a `.do` file you can hand to a journal's replication office or a co-author who refuses to leave Stata.

## Philosophy

1. **Stata idioms, not Python-translated.** `reghdfe`, not "statsmodels analogue of reghdfe". `esttab`, not "Stata's stargazer".
2. **Reproducible .do files.** Every code block below is runnable after `use data.dta, clear`. No Jupyter, no notebooks — just do-files and log files.
3. **Full pipeline, not just regressions.** Stata users historically over-invest in Step 5 (modeling) and under-invest in Steps 1–4 and 6–8. This skill treats them as first-class.
4. **Rich outputs.** Every step yields at least one table (`.tex`/`.rtf`) or figure (`.pdf`/`.png`) — never a coefficient printed to the Results window and forgotten.
5. **Progressive disclosure.** `SKILL.md` gives the canonical command at each step; [`references/`](references/) holds variant-specific depth (dozens of tests, estimator-specific diagnostics, graph recipes).

## SkillOpt-style execution gate

Use this long playbook as a seed skill, not as a script to exhaustively apply. SkillOpt discipline: treat each local `.do`-file change as a candidate patch that must beat a selection check and survive a held-out check before it becomes reusable boilerplate. Before writing or revising a `.do` file, compress the user's request into a task-local `best_skill` card:

```text
best_skill: <mode + design + artifact target>
train_signal: <current failure, user goal, or missing evidence>
selection_split: <focal dataset/spec/output used to judge the candidate>
heldout_gate: <checks the patch must pass beyond the focal example>
accepted_patterns: <rules to reuse after validation>
rejected_patterns: <failed shortcuts not to retry without new evidence>
patch_scope: <one estimator/sample/export/robustness change>
reject_if: <conditions that force rollback to the last passing spec>
```

1. **Route card**: record the mode (`econ`, `epi`, or `ml-causal`), estimand, identification design, focal outcome/treatment, Stata command family, and required artifacts.
2. **Bounded edit**: change one decision at a time (sample rule, estimator command, fixed effects, clustering, export format, or robustness check). Prefer the smallest patch that can pass validation.
3. **Selection split discipline**: treat the user's immediate failure or requested artifact as the selection split. Reserve at least one alternate outcome, sample window, estimator command family, or export target as the held-out gate.
4. **Held-out gate**: define checks before running code: `isid`/duplicate status, merge assertions, treatment support, missingness thresholds, expected table/figure files, and one non-focal robustness/specification that the change must not break.
5. **Reject buffer**: if a candidate spec fails the gate, log the failure, `.do` diff, and gate output in `analysis_log.md` or the Stata log; revert to the last passing spec and do not retry the same unchecked pattern.
6. **Slow/meta update**: at the end of the task, write down `accepted_patterns` and `rejected_patterns` from the trajectory. Do not widen the canonical `.do` template from a single passing run.
7. **Promote only after validation**: only turn a one-off fix into reusable `.do` boilerplate after it passes the current data and at least one alternate outcome/sample/specification.

---

## Three domain modes (default = AER econ; alternates = epi & ML-causal)

The default playbook above is **AER-style applied econometrics** — the AEA convention: written-out estimating equation, identifying assumption, design horse-race, full robustness gauntlet. The skill **also** ships two parallel sub-pipelines for the other two big causal-inference traditions, each reusing the same Steps 1–4 (cleaning / construction / Table 1 / diagnostics) and Step 8 (tables/figures) — only Step 5 (estimator) and Step 6/7 swap commands:

| Mode | Reader convention | Step-5 estimator stack | Reporting stack | Jump to |
|---|---|---|---|---|
| **Default — Applied Econ (AER / QJE / AEJ)** | "Show the equation + identifying assumption + design horse-race; controls visible; clustered SE" | DID / IV / RD / SCM / matching / `reghdfe` HDFE | AER house-style multi-column `esttab` / `outreg2` / `coefplot` + 8-section paper layout | Steps 1 → 8 (entire playbook below) |
| **Mode A — Epidemiology / Public Health** | "STROBE / TRIPOD-AI; target trial protocol; doubly-robust estimand; absolute & relative risk; KM survival" | Target-trial emulation · IPTW (`teffects ipw`) · IPWRA / AIPW (`teffects ipwra` / `teffects aipw`) · g-formula (`gformula`) · TMLE (`eltmle`) · Mendelian randomization (`mrrobust` IVW / `mregger` / `mrpresso`) · KM/Cox/AFT (`sts`/`stcox`/`streg`/`strmst2`) | Same `esttab` + risk-difference / hazard-ratio / E-value rows | §A. Epidemiology pipeline |
| **Mode B — ML Causal Inference** | "DML / meta-learners / causal forest / DR-learner; CATE distribution; policy value" | DML (`ddml` / `pdslasso`) · S/T/X/R/DR-Learner (`ddml interactive`) · GRF causal forest (`crforest` / `cforest`) · BART / BCF (external Python via `python_user`) · matrix completion (external) | `esttab` ML horse-race + `crforest` CATE plot + policy-value table | §B. ML causal pipeline |

**How to invoke a non-default mode** (Claude / agent picks this up from the user's wording):

| User says... | Mode the skill switches to |
|---|---|
| "Run a DID / IV / RD / event study", "AER table", "applied micro" | Default (AER econ) — Steps 1 → 8 |
| "Target trial emulation", "g-formula", "IPTW", "TMLE", "Mendelian randomization", "STROBE / TRIPOD", "公共健康 / 流行病学", "epi pipeline", "RWE study", "cohort study", "case-control" | Mode A (Epi) — §A |
| "DML", "double machine learning", "ddml", "causal forest", "crforest", "meta-learner", "CATE", "policy learning", "ML causal", "因果机器学习" | Mode B (ML causal) — §B |
| "Mix" (e.g. "estimate DID + then ML CATE on the heterogeneity") | Default + Mode B in sequence — every estimator stores results via `eststo`, drop them all into one `esttab` for the horse-race column |

The three modes share **the same Step 1–4 cleaning / Table 1 / diagnostics scaffolding, the same Step 8 export stack, and the same DAG-first identification logic** — switching modes only changes which Step-5 command family you reach for. If you only want descriptive stats / Table 1 / a balance check, the AER `tabstat` / `balancetable` / `asdoc` calls in Step 3 work identically across all three modes.

> **Stata-specific caveat for Mode B**: Stata's first-party ML-causal coverage is thinner than Python/R. For Dragonnet / TARNet / CEVAE / cfcausal / fairness audit, call out to Python via Stata 18's `python:` / `python script` block (or shell out to a sister `.py`) and read the result back via `frame` or `import delimited`. The skill prefers native Stata commands (`ddml`, `pdslasso`, `crforest`) where they exist, and explicitly marks the Python callouts in §B.

---

## Default Output Spec — Economics Empirical Paper

This skill defaults to the **applied-economics paper convention**. Unless the user explicitly asks for a single point estimate, every `.do`-file run produces the full publication-ready output set below. Treat it as the contract of Step 8 — **mandatory**, not opt-in.

### Required tables (always produced)

| # | Table | Stata source | Saves to |
|---|---|---|---|
| **T1** | Summary statistics & balance (treated vs control, with SMD / p-values) | `balancetable` + `asdoc sum` (Step 3) | `tables/table1_balance.{tex,rtf,xlsx,docx}` |
| **T2** ★ | **Main results — multi-column regression M1→M6** (progressive controls + FE) | `eststo` 6 specs → `esttab` (Step 5–6) | `tables/table2_main.{tex,rtf,xlsx,docx}` |
| **T3** | Mechanism / outcome ladder — same treatment, 3+ outcomes side-by-side | loop `eststo: reghdfe` over outcomes → `esttab` (Step 7) | `tables/table3_mechanism.{tex,rtf,xlsx,docx}` |
| **T4** | Heterogeneity — subgroup × main coef (gender, age, region, …) | subgroup `eststo` + `suest` Wald → `esttab` (Step 7) | `tables/table4_heterogeneity.{tex,rtf,xlsx,docx}` |
| **T5** | Robustness battery — alt SE / cluster / sample / placebo, in **one** table | `eststo` × variants → `esttab` (Step 6) | `tables/table5_robustness.{tex,rtf,xlsx,docx}` |

> **★ Table 2 is the centerpiece of every economics paper.** It is the multi-column regression table that walks the reader from raw correlation (M1) to the fully-specified design (M6: 2-way FE + interacted FE + cluster-robust SE). Do **not** collapse it into a single column. Do **not** report only the headline coefficient. The progression *is* the credibility argument: if M1→M6 is monotone and stable, the design is plausibly identifying; if it collapses on adding FE, that *is* the result.
>
> **Canonical 6 columns, in order:**
> 1. **M1** raw bivariate (`reg y treat`)
> 2. **M2** + demographics (`+ age + edu`)
> 3. **M3** + sector controls (`+ tenure / firm_size`)
> 4. **M4** + unit FE (`reghdfe ..., absorb(unit)`)
> 5. **M5** + 2-way FE (`absorb(unit year)`)
> 6. **M6** + interacted FE (`absorb(unit year i.industry#i.year)`) with `vce(cluster unit)`

### Required figures (always produced)

| # | Figure | Stata source | Saves to |
|---|---|---|---|
| **F1** | Trend / motivation — treated vs control over time, with policy line | `collapse (mean) y, by(year treat)` → `twoway line` (Step 3) | `figures/fig1_trend.pdf` (+ `.png`) |
| **F2** | Event-study coefficients with 95% CI, base period at –1 | `eventstudyinteract` / `csdid` / `coefplot, keep(*.rel)` (Step 5) | `figures/fig2_event_study.pdf` |
| **F3** | Coefficient plot across specs M1→M6 | `coefplot m1 m2 m3 m4 m5 m6, keep(treat) vertical` (Step 8) | `figures/fig3_coefplot.pdf` |
| **F4** | Robustness / sensitivity curve — `bacondecomp` plot, `honestdid` plot, or cluster-comparison forest | scenario-specific (Step 6) | `figures/fig4_sensitivity.pdf` |

### Output file layout (default)

```
project/
├── tables/    table1_balance.{tex,rtf,xlsx,docx}  table2_main.{tex,rtf,xlsx,docx}
│              table3_mechanism.{tex,rtf,xlsx,docx}   table4_heterogeneity.{tex,rtf,xlsx,docx}
│              table5_robustness.{tex,rtf,xlsx,docx}
└── figures/   fig1_trend.{pdf,png}        fig2_event_study.{pdf,png}
               fig3_coefplot.{pdf,png}     fig4_sensitivity.{pdf,png}
```

Every table → `.tex` (LaTeX `booktabs`) **and** `.rtf` (Word) **and** `.xlsx` (Excel) **and** `.docx` (Word OOXML). Every figure → `.pdf` (vector for LaTeX) **and** `.png` at ≥300 dpi (slides / web).

### When to deviate

- **Single quick estimate** — produce only the relevant cell, but warn that the standard deliverable is the full set above and offer to run it.
- **Design does not support a figure** (cross-section → no event study) — skip with a printed `display` note explaining why; do **not** silently drop.
- **N=1 treated unit (`synth`)** — replace F1/F2 with the SCM trajectory + placebo distribution from `synth_runner`; T1–T5 still apply.

---

## Required packages

```stata
* Run once on a fresh Stata install:
ssc install reghdfe,         replace
ssc install ftools,          replace       // dependency of reghdfe / ivreg2
ssc install ivreg2,          replace
ssc install ranktest,        replace       // dependency of ivreg2
ssc install ivreghdfe,       replace       // ivreg2 × reghdfe: high-dim FE IV
ssc install ppmlhdfe,        replace       // Poisson with HD FE
ssc install csdid,           replace       // Callaway–Sant'Anna (2021)
ssc install drdid,           replace       // dependency of csdid
ssc install did_imputation,  replace       // Borusyak–Jaravel–Spiess (2024)
ssc install eventstudyinteract, replace    // Sun & Abraham (2021)
ssc install sdid,            replace       // Synthetic DID (Arkhangelsky et al. 2021)
ssc install did_multiplegt_dyn, replace    // de Chaisemartin & D'Haultfœuille
ssc install bacondecomp,     replace       // Goodman-Bacon (2021)
ssc install honestdid,       replace       // Rambachan–Roth (2023) PT sensitivity
ssc install rdrobust,        replace       // Calonico–Cattaneo–Titiunik RD
ssc install rddensity,       replace       // McCrary / Cattaneo et al. density test
ssc install synth,           replace       // Abadie–Diamond–Hainmueller SCM
ssc install synth_runner,    replace       // SCM with placebos + inference
ssc install psmatch2,        replace       // propensity-score matching
ssc install ebalance,        replace       // entropy balancing
ssc install coefplot,        replace
ssc install estout,          replace       // provides estout / esttab / eststo
ssc install outreg2,         replace
ssc install asdoc,           replace       // one-click Word/Excel tables
ssc install binscatter,      replace
ssc install balancetable,    replace
ssc install winsor2,         replace
ssc install xtable,          replace       // better xtreg output tables
ssc install boottest,        replace       // wild cluster bootstrap (Roodman et al.)
ssc install ritest,          replace       // randomization inference
ssc install rwolf,           replace       // Romano–Wolf multiple-testing
ssc install moremata,        replace       // Mata extensions (dep for several)
ssc install mdesc,           replace       // missing data description
ssc install missings,        replace       // missings dropvars, report
ssc install unique,          replace       // unique IDs in panel
ssc install schemepack,      replace       // modern publication themes
```

---

## The 8 Steps — Canonical Pipeline (mapped to AER paper sections)

```
┌──────────────────────────────────────────────────────────────────────┐
│ Step −1 Pre-Analysis Plan (PAP)   power/sampsi/clustersampsi/MDE     │
│ Step 0  Sample log + data contract sample_log/assert/xtdescribe/JSON │
│ Step 1  Data import & cleaning    use/import/destring/misstable/merge│
│ Step 2  Variable construction     gen/egen/winsor2/xtile/xtset/L.F.D.│
│ Step 2.5 Empirical strategy       equation × ID assumption + pre-reg │
│ Step 3  Descriptive statistics    tabstat/balancetable/asdoc/pwcorr  │
│ Step 3.5 Identification graphics  event-study/1st-stage/McCrary/love │
│ Step 4  Diagnostic tests          sktest/hettest/xtserial/vif/dfuller│
│ Step 5  Baseline modeling         reghdfe/ivreg2/csdid/rdrobust/synth│
│ Step 6  Robustness battery        bacondecomp/honestdid/rwolf/boottest│
│ Step 7  Further analysis          triple-diff/subgroup/medsem/margins│
│ Step 8  Tables & figures          esttab/outreg2/coefplot/rdplot     │
└──────────────────────────────────────────────────────────────────────┘
```

The 8 steps mirror the canonical sections of an applied AER / QJE / AEJ paper. Each step is one paper section and emits a paper-ready artifact on disk:

```
Paper section               Step  Stata moves
─────────────────────────── ───── ────────────────────────────────────────────────
Pre-Analysis Plan           −1    power/sampsi + freeze protocol.do to disk
§1. Data                     0    sample_log + 5-check data contract → JSON
§1. Data                     1    use/import/destring/misstable/merge assert/xtset
§1. Data                     2    gen/egen/winsor2/xtile/L./F./D./CPI deflation
§1.1 Descriptives (Table 1)  3    tabstat · balancetable · asdoc · pwcorr · twoway
§2. Empirical Strategy       2.5  write equation + ID assumption → strategy.do
§3. Identification graphics  3.5  event-study · 1st-stage F · McCrary · love · SCM
§3.5 Diagnostics             4    swilk · hettest · xtserial · vif · dfuller · hausman
§4. Main Results (Table 2)   5    M1→M6 progressive controls + FE  (eststo + esttab)
§5. Heterogeneity (Table 3)  7    margins/marginsplot · subgroup · medsem
§6. Mechanisms / Channels    7    medsem/khb · outcome ladder · DDD interactions
§7. Robustness gauntlet      6    bacondecomp · honestdid · psacalc · boottest · ritest · rwolf
§8. Replication package      8    esttab + outreg2 + coefplot + reproducibility stamp
```

Below is the canonical command at each step. **All examples share one running narrative** — a labor-economics panel where `training` (treatment) affects `log_wage` (outcome), with covariates `age`, `edu`, `tenure`, panel keys `worker_id` / `firm_id` / `year`. Variable names and parameter values are **illustrative**; substitute the real ones from the user's dataset. Only command names and option *shapes* are normative.

> **When a step has many variants** (e.g. staggered DID has 5 estimators; heteroskedasticity has 4 classic tests), SKILL.md shows the one you reach for first and links to `references/NN-<topic>.md` for the rest. **Read the reference file when the user's case doesn't fit the default.**

---

## Paper-ready figure & table inventory (what to produce by section)

A modern AER paper has **5–7 figures** and **3–5 main tables** + an appendix robustness table. Every step below leaves at least one numbered artifact on disk. Default file names assume parallel `.tex` / `.rtf` exports (the agent should produce both so co-authors can edit in Word, and the build system can use LaTeX):

| § | Artifact | Stata primitive | Filenames |
|---|---|---|---|
| §1 | **Figure 1**: raw trends / treatment rollout | `collapse` + `twoway line` · `heatplot` for staggered rollout | `figures/fig1_trend.{pdf,png}` |
| §1 | **Table 1**: summary stats (full / treated / control + Δ + SMD) | `balancetable` · `asdoc sum, by()` · `tabstat` | `tables/table1_balance.{tex,rtf,xlsx,docx}` |
| §3 | **Figure 2**: identification graphic (event-study / first-stage / McCrary / RD scatter / SCM trajectory) | `coefplot` after `eventstudyinteract`/`csdid` · `binscatter` · `rdplot` · `rddensity, plot` · `synth` | `figures/fig2_event_study.{pdf,png}` |
| §4 | **Table 2**: main results — progressive controls M1→M6 | `eststo` 6 specs → `esttab` | `tables/table2_main.{tex,rtf,xlsx,docx}` |
| §4 | **Table 2-bis**: design horse-race (OLS / IV / DID / matching) | `eststo` mix + `esttab` | `tables/table2b_designs.{tex,rtf,xlsx,docx}` |
| §4 | **Figure 3**: coefficient plot across specs | `coefplot m1 m2 m3 m4 m5 m6, keep(treat)` | `figures/fig3_coefplot.{pdf,png}` |
| §5 | **Table 3**: heterogeneity by subgroup | `eststo` per slice + `esttab` + `suest` Wald | `tables/table3_heterogeneity.{tex,rtf,xlsx,docx}` |
| §5 | **Figure 4**: dose-response / margins-by-quartile | `xtile` + `margins` + `marginsplot` | `figures/fig4_dose.{pdf,png}` |
| §6 | **Table 4**: mechanism / outcome ladder | loop `eststo: reghdfe` over outcomes → `esttab` | `tables/table4_mechanism.{tex,rtf,xlsx,docx}` |
| §7 | **Table A1**: robustness master (one column per check) | `eststo` × variants → `esttab` | `tables/tableA1_robustness.{tex,rtf,xlsx,docx}` |
| §7 | **Figure 5**: spec curve — coefficient + 95% CI across all specs | hand-rolled spec loop + `twoway rcap` | `figures/fig5_spec_curve.{pdf,png}` |
| §7 | **Figure 6**: sensitivity (HonestDiD / Oster / E-value) | `honestdid, coefplot` · `psacalc plot` · `evalue` table | `figures/fig6_sensitivity.{pdf,png}` |
| §8 | **Replication bundle**: all tables in one document | `esttab ..., append` to one `.tex` / `.rtf` · `texdoc` | `replication/paper_tables.{tex,rtf,xlsx,docx}` |

> Every Stata estimator above stores results via `eststo` and can be passed straight into `esttab` / `coefplot` / `outreg2`. Don't hand-roll LaTeX, and don't render Word from `outsheet`/`putexcel` matrices — `esttab` and `outreg2` apply book-tab borders, AER-style stars, and the right SE label automatically. For deeper export recipes (LaTeX / Word / Markdown variants, `texdoc`, `frmttable`), see [`references/08-tables-plots.md`](references/08-tables-plots.md).

---

## Export cookbook — LaTeX / Word / RTF in one block

Stata's export stack is more fragmented than Python's StatsPAI. Three tiers, picked by **scope**:

| Tier | Use when | API | Hot options |
|---|---|---|---|
| **1. Single multi-column table** | Exporting *one* Table 2 / Table 3 / Table A1 with progressive columns | **`.tex` / `.rtf`**: `esttab` with `booktabs`<br>**`.xlsx` / `.docx`**: `outreg2` (esttab's native Office export is a data dumper, not a publication formatter — outreg2 produces properly formatted Word/Excel with borders, aligned stars, and AER-style layout) | **`esttab`** for tex/rtf: `keep()`, `drop()`, `mtitles()`, `stats(N r2 r2_a, labels(...))`, `star(* 0.10 ** 0.05 *** 0.01)`, `label`, `booktabs`, `addnotes()`.<br>**`outreg2`** for xlsx/docx: `label dec(3)`, `addtext()` for FE indicators, `replace` first / `append` subsequent columns.<br>Always emit all four formats — esttab for tex/rtf in a `foreach ext in tex rtf` loop, outreg2 for xlsx/docx in a separate `foreach ext in xlsx docx` loop. |
| **2. Multi-panel paper format** (Tables 2 + 3 + A1 + A2 in one file) | Producing the paper-tables block — main + heterogeneity + robustness + placebo as a single document | `esttab ... using "paper.tex", replace` for first panel; subsequent `esttab ... using "paper.tex", append` for each next panel; `texdoc init "paper.tex"` for full LaTeX with prose. Repeat for `.rtf`/`.xlsx`/`.docx` bundles. | first panel: `replace`; subsequent: `append`; surround with `texdoc` for headings |
| **3. Full session bundle** (the Stata 17+ `collect` equivalent) | Replication appendix that mixes summary stats + balance + multiple regression tables + headings + prose in **one** file | `collect create paper`<br>`collect get summary, ...`<br>`collect get est ...`<br>`collect layout ...`<br>`collect export "paper.xlsx"` (also `.docx`/`.html`/`.tex`/`.md`) | Stata 17+ only; for older Stata use `texdoc` / `markdoc` |

**Journal styling — pick the right `star` levels and SE label.** The AEA convention is `* 0.10 ** 0.05 *** 0.01` and SE label "Standard errors in parentheses"; QJE / Econometrica / RES variants only differ in stars / notes / fonts. Define an `esttab` wrapper once at the top of the do-file:

```stata
* Top of master.do — journal house-style wrapper
local AER_STAR  "* 0.10 ** 0.05 *** 0.01"
local AER_NOTES "Cluster-robust standard errors in parentheses. * p<0.10, ** p<0.05, *** p<0.01."
local AER_STATS stats(N r2_a, labels("N" "Adj. R²"))

* LaTeX + RTF via esttab (booktabs for tex)
* esttab m1 m2 m3 using "tables/table2.tex", replace ///
*     se star(`AER_STAR') label booktabs `AER_STATS' addnotes(`AER_NOTES')
* esttab m1 m2 m3 using "tables/table2.rtf", replace ///
*     se star(`AER_STAR') label `AER_STATS' addnotes(`AER_NOTES')

* Excel + Word via outreg2 (publication-grade Office formatting)
* First column: replace; subsequent: append
* outreg2 using "tables/table2.xlsx", replace label dec(3) ///
*     keep(training age edu tenure) addtext(Worker FE, Yes, Year FE, Yes)
* outreg2 using "tables/table2.xlsx", append   label dec(3) ///
*     keep(training age edu tenure region) addtext(Worker FE, Yes, Year FE, Yes, Region, Yes)
```

**Multi-format export pattern** — emit `.tex` and `.rtf` via `esttab`, then `.xlsx` and `.docx` via `outreg2`. Never use `esttab ... using "... .xlsx"` or `esttab ... using "... .docx"` — esttab's native Office export is a raw data dumper, not a publication formatter:

```stata
* LaTeX + RTF — use esttab (booktabs for tex, rich text for rtf)
foreach ext in tex rtf {
    esttab m1 m2 m3 using "tables/table2_main.`ext'", ///
        replace se star(* 0.10 ** 0.05 *** 0.01) ///
        label booktabs mtitles("(1)" "(2)" "(3)") ///
        stats(N r2_a, labels("N" "Adj. R²")) ///
        addnotes("Cluster-robust SE in parentheses. * p<0.10, ** p<0.05, *** p<0.01.")
}

* Excel + Word — use outreg2 (proper Office table formatting, aligned stars, borders)
* First model: replace
eststo m1: qui reghdfe log_wage training age edu tenure, absorb(worker_id year) vce(cluster worker_id)
outreg2 using "tables/table2_main.xlsx", replace label dec(3) ///
    keep(training age edu tenure) ///
    addtext(Worker FE, Yes, Year FE, Yes)

* Subsequent models: append
eststo m2: qui reghdfe log_wage training age edu tenure region, absorb(worker_id year) vce(cluster worker_id)
outreg2 using "tables/table2_main.xlsx", append label dec(3) ///
    keep(training age edu tenure region) ///
    addtext(Worker FE, Yes, Year FE, Yes, Region, Yes)

* docx follows the same pattern but with the .doc extension
outreg2 using "tables/table2_main.doc", replace label dec(3) ///
    keep(training age edu tenure) ///
    addtext(Worker FE, Yes, Year FE, Yes)
eststo m2
outreg2 using "tables/table2_main.doc", append label dec(3) ///
    keep(training age edu tenure region) ///
    addtext(Worker FE, Yes, Year FE, Yes, Region, Yes)
```

**Figures always export to both `.pdf` and `.png` at ≥300 dpi** (vector for LaTeX, raster for slides/web/Word embedding):

```stata
graph export "figures/fig1_trend.pdf", replace
graph export "figures/fig1_trend.png", replace width(2400) height(1800)
```

For the `collect` / `texdoc` / `markdoc` cookbook (Stata 17+ multi-panel paper bundle and prose+tables PDF/Word generation), see [`references/08-tables-plots.md`](references/08-tables-plots.md).

---

## Step −1 — Pre-Analysis Plan (pre-data; AEA RCT Registry style)

Before touching the data, write down (a) the population, (b) the design, (c) the **minimum detectable effect (MDE)** under the planned sample size and α=0.05, β=0.20. Persist the result as `protocol.do` so a referee can verify the design was powered before, not after, the data were seen.

```stata
* Two-sample MDE (continuous outcome, Cohen's d framing)
power twomeans 0, diff(0.2) sd(1) power(0.80) alpha(0.05)
* → required n per arm

* Cluster-randomized RCT — solve for n_clusters given ICC
power twomeans 0, diff(0.2) sd(1) power(0.80) k1(50) rho(0.05) cluster
* → required clusters per arm under ICC=0.05, cluster size 50

* DID power (Frison–Pocock / Bloom 1995): use -sampsi- + -clustersampsi-
* (no native `power did`; for staggered DID see references/05-modeling.md §5.4)
sampsi 0 0.15, sd(1.0) alpha(0.05) power(0.80) n1(.) n2(.)

* RD power — McCrary-style: solve via Monte Carlo with -simulate-
* (see references/05-modeling.md §5.5 RD power template)

* Persist the protocol — referee will ask whether design was powered ex ante
file open f using "protocol.do", write replace
file write f "* Pre-analysis plan — frozen `c(current_date)' `c(current_time)'" _n
file write f "* Population:    manufacturing workers 2010-2020" _n
file write f "* Treatment:     training (binary)" _n
file write f "* Outcome:       log_wage" _n
file write f "* Design:        staggered DID, csdid (Callaway-Sant'Anna 2021)" _n
file write f "* MDE:           0.05 log points at 80% power, α=0.05" _n
file write f "* N planned:     ~12,000 worker-years" _n
file close f
```

Save this `.do` file in version control **before** running Step 1. AEA RCT Registry / OSF preregistration tools accept it as the analysis-plan exhibit.

---

## Step 0 — Sample-construction log & 5-check data contract

An AER §1 *Data* section has three jobs: (a) describe sources, (b) document **every** sample restriction (the "footnote 4" sample log), (c) lock the panel structure. Stata users typically chain `keep` / `drop` commands in a single do-file with no count log, then can't reconstruct the analysis sample for the response letter. The data contract is the cure.

### 0.1 Sample-construction log (footnote 4)

```stata
use "raw.dta", clear
matrix sample_log = J(0, 2, .)
local row 0
local n0 = _N
local ++row
matrix sample_log = (nullmat(sample_log) \ `row', `n0')
display "Step 0. raw:                          N = " %12.0fc `n0'

drop if missing(wage)
local n1 = _N
local ++row
matrix sample_log = (nullmat(sample_log) \ `row', `n1')
display "Step 1. drop missing wage:            N = " %12.0fc `n1' "  (Δ " %10.0fc `n0' - `n1' ")"

drop if !inrange(age, 18, 65)
local n2 = _N
local ++row
matrix sample_log = (nullmat(sample_log) \ `row', `n2')
display "Step 2. drop age outside 18-65:       N = " %12.0fc `n2' "  (Δ " %10.0fc `n1' - `n2' ")"

keep if inlist(industry, "manuf", "construction", "transport")
local n3 = _N
local ++row
matrix sample_log = (nullmat(sample_log) \ `row', `n3')
display "Step 3. keep target industries:       N = " %12.0fc `n3' "  (Δ " %10.0fc `n2' - `n3' ")"

* Persist to JSON (for paste into footnote 4)
file open f using "artifacts/sample_construction.json", write replace
file write f "{" _n
file write f `"  "step_0_raw":     `=sample_log[1,2]',"' _n
file write f `"  "step_1_wage":    `=sample_log[2,2]',"' _n
file write f `"  "step_2_age":     `=sample_log[3,2]',"' _n
file write f `"  "step_3_indust":  `=sample_log[4,2]'"' _n
file write f "}" _n
file close f
```

Paste the `display` lines verbatim as footnote 4 of the paper.

### 0.2 Five-check data contract (go / no-go gate)

```stata
* (1) Shape
display "Check 1. n_obs = " _N

* (2) Dtypes on key vars — assert types are numeric where required
foreach v in wage training worker_id year age edu tenure {
    capture confirm numeric variable `v'
    if _rc {
        display as error "Check 2 FAILED: `v' is not numeric — fix before any panel command"
        exit 198
    }
}
display "Check 2. dtypes OK on all key vars"

* (3) Missingness pattern on key vars
mdesc wage training worker_id year age edu tenure                 // ssc install mdesc
foreach v in wage training worker_id year {
    qui count if missing(`v')
    if r(N) > 0 {
        display as error "Check 3 FAILED: `v' has " r(N) " missing — fix before estimation"
        exit 198
    }
}

* (4) Duplicate (id, time) — fatal for panel methods
duplicates report worker_id year
duplicates tag worker_id year, gen(dup)
qui count if dup > 0
if r(N) > 0 {
    display as error "Check 4 FAILED: " r(N) " duplicate (worker_id, year) rows"
    exit 198
}
drop dup

* (5) Panel balance
xtset worker_id year
xtdescribe
qui xtdes
local n_balanced = r(N)
display "Check 5. panel n=" _N " (balanced cells if `n_balanced' equals expected unit×period)"

* MCAR sniff test (Rubin) — if missing(y) is associated with covariates,
* listwise deletion biases the estimate. Use `mi` / IPW instead.
gen byte miss_y = missing(wage)
foreach cov in age edu tenure {
    qui ttest `cov', by(miss_y)
    if r(p) < 0.05 {
        display as error "WARNING: y-missingness associates with `cov' (p=" %5.3f r(p) ")."
        display as error "         -> NOT MCAR, use -mi impute- or IPW, NOT listwise drop."
    }
}
drop miss_y

* Persist contract
file open f using "artifacts/data_contract.json", write replace
file write f "{" _n
file write f `"  "n_obs": `=_N',"' _n
file write f `"  "panel": "worker_id × year","' _n
file write f `"  "treatment": "training","' _n
file write f `"  "outcome":   "log_wage""' _n
file write f "}" _n
file close f
```

If any assertion fires, **stop** and fix it. Stata estimators silently drop NaN rows, the most common source of "mysterious sample-size shrinkage" bugs in the response letter.

---

### Step 1 — Data import & cleaning

Deeper patterns: [references/01-data-cleaning.md](references/01-data-cleaning.md) — reading Excel/CSV/SAS/SPSS, `destring` on numeric-looking strings, `misstable` patterns, `duplicates` tagging, `merge` with `assert(match using)`, `xtset` balance checks, spells / gaps, labels.

```stata
* 1a. Load + first look
use "raw.dta", clear
describe, short
summarize
misstable summarize
mdesc                                   // missing-data report

* 1b. Dtypes — destring strings-that-should-be-numeric
destring year wage, replace force       // force: convert non-numeric to .
gen hire_date = date(hire_date_str, "YMD"); format hire_date %td

* 1c. Missing values — decide PER VARIABLE
local key_vars "wage training worker_id year"
foreach v of local key_vars {
    drop if missing(`v')
}
sum tenure, detail
replace tenure = r(p50) if missing(tenure)      // median-impute
gen byte tenure_miss = missing(tenure)           // keep the flag

* 1d. Outliers — flag first (winsorize in Step 2)
egen wage_z = std(wage)
count if abs(wage_z) > 4
display "Flagged |z|>4 on wage: " r(N)

* 1e. Deduplicate on panel key
duplicates report worker_id year
duplicates tag worker_id year, gen(dup)
assert dup == 0                                  // hard-fail if panel key not unique
drop dup

* 1f. Merge with assert — never silently lose rows
merge m:1 firm_id using "firm_chars.dta", ///
    assert(match using master) keep(master match) nogen

* 1g. Panel structure
xtset worker_id year                              // declares panel
xtdescribe                                        // balance summary
tab year                                          // observations per year
```

**Key principle**: all row exclusions are explicit, counted, logged. No command in Steps 2+ should silently drop rows.

---

### Step 2 — Variable construction & transformation

Deeper patterns: [references/02-data-transformation.md](references/02-data-transformation.md) — log / ihs / Box–Cox, within-group `winsor2`, `xtile` and custom cuts, `egen` recipes, time-series operators (`L.`, `F.`, `D.`, `S.`), CPI deflation, staggered-DID timing construction.

```stata
* 2a. Log / IHS
gen log_wage = log(max(wage, 1))                  // floor at 1
gen ihs_assets = asinh(assets)                    // handles 0 / negative

* 2b. Winsorize 1/99
winsor2 wage, cuts(1 99) suffix(_w1) by(year)     // within-year winsorize

* 2c. Standardize
egen age_std = std(age)

* 2d. Categorical encoding (factor variables — use i. inside regressions)
* Explicit dummies only when needed for export
tab industry, gen(ind_)
drop ind_1                                        // base category

* 2e. Interactions & polynomials — use c. and i. inline in reg commands
gen age_sq = age^2
gen trt_x_edu = training * edu

* 2f. Panel operators (xtset is required for L./F./D. to work)
xtset worker_id year
gen log_wage_l1 = L.log_wage
gen log_wage_f1 = F.log_wage
gen d_log_wage  = D.log_wage

* 2g. Within-unit mean (egen)
egen wage_mean_i = mean(log_wage), by(worker_id)

* 2h. Treatment timing for staggered DID
bysort worker_id (year): egen first_treat = min(cond(training==1, year, .))
gen rel_time = year - first_treat
replace rel_time = . if missing(first_treat)      // never-treated = .
gen never_treated = missing(first_treat)

* 2i. Real values (CPI deflation)
merge m:1 year using "cpi.dta", keep(master match) nogen
sum cpi if year == 2010
gen wage_real = wage * r(mean) / cpi
```

---

### Step 2.5 — Empirical strategy (write the equation + identifying assumption)

This is the heart of an AER paper. **Before any code**, write down the equation explicitly and state the identifying assumption. Vague identification language is the single most common reason a referee rejects an applied paper. Persist the strategy as `strategy.do` (or `.md`) so it is a dated, version-controlled artifact — *not* a post-hoc rationalization written after seeing the coefficient.

#### Equation × identifying assumption × Stata estimator (decision table)

| Design | Estimating equation | Identifying assumption | Stata estimator |
|---|---|---|---|
| 2×2 DID | `Y_it = α_i + λ_t + β·D_it + X'γ + ε_it` | parallel trends conditional on X | `reghdfe Y c.D#c.post X, absorb(i t) vce(cluster i)` |
| Event-study (CS / SA) | `Y_it = α_i + λ_t + Σ_{e≠-1} β_e · 1{t-G_i = e} + ε_it` | no anticipation + group-time PT | `csdid` / `eventstudyinteract` / `did_imputation` |
| 2SLS | `Y_i = α + β·D_i + X'γ + ε_i;  D_i = π·Z_i + X'δ + u_i` | exclusion + relevance + monotonicity | `ivreg2` / `ivreghdfe` |
| Sharp RD | `Y_i = α + β·1{X_i ≥ c} + f(X_i) + ε_i` (local poly) | continuity of E[Y(0)\|X] at c, no manipulation | `rdrobust` (+ `rddensity`) |
| SCM | `Ŷ_1t(0) = Σ_j ŵ_j Y_jt`, τ_t = `Y_1t − Ŷ_1t(0)` for t≥T_0 | pre-period fit + interpolation validity | `synth` / `synth_runner` / `sdid` |
| Selection-on-observables (matching/IPW) | `E[Y_i(d) \| X_i] = E[Y_i \| D=d, X_i]` | unconfoundedness + overlap | `teffects psmatch / ipw / aipw / ipwra`, `ebalance` |

#### Design picker (when the user is unsure)

```
                 ┌─ running var + cutoff ───────────────── RDD       (rdrobust)
                 │
                 ├─ exogenous instrument Z ─────────────── IV/2SLS   (ivreg2 / ivreghdfe)
data + question ─┤
                 ├─ pre/post × treat/control ─┬ 2 periods  ── 2×2 DID (reghdfe / xtreg)
                 │                            └ staggered  ── CS / SA / BJS  (csdid / eventstudyinteract / did_imputation)
                 │
                 ├─ 1 treated unit + donor pool + long pre ── SCM    (synth / synth_runner / sdid)
                 │
                 ├─ high-dim X, selection-on-observables ── ML causal (ddml / crforest — see §B)
                 │
                 └─ none of the above ──────────────────── matching + sensitivity (teffects + evalue)
```

#### Pre-registration `strategy.do` template

```stata
*--- strategy.do — empirical-strategy pre-registration ---
* Frozen `c(current_date)' `c(current_time)'  (Git SHA: <paste>)
* Population:    manufacturing workers, 2010–2020, balanced panel
* Treatment:     training (binary, staggered adoption)
* Outcome:       log_wage (CPI-deflated 2010 USD)
* Estimand:      ATT on the treated, dynamic horizon -4..+4
*
* Estimating equation (paste from the §2.5 row that matches the design):
*   log_wage_it = α_i + λ_t + Σ_{e≠-1} β_e · 1{t - G_i = e} + ε_it
*
* Identifying assumption:
*   1. No anticipation:    E[Y_it(0) | t < G_i] = E[Y_it(0) | never-treated]
*   2. Group-time PT:      Δ E[Y_it(0)] is the same across treatment cohorts
*
* Auto-flagged threats (must defend in §2):
*   - Selection of G_i on Y_i(0)            -> bacondecomp + honestdid sensitivity
*   - Spillover across worker_id within firm -> cluster at firm_id, also try firm_id × year
*   - Anticipation in the year before adoption -> include lead in event study
*
* Fallback estimators (Step 6 robustness):
*   - eventstudyinteract  (Sun-Abraham 2021)
*   - did_imputation      (Borusyak-Jaravel-Spiess 2024)
*   - sdid                (Synthetic DID)
```

Commit `strategy.do` **before** running Step 5 / Step 6. The `git log` of this file *is* the analysis plan.

---

### Step 3 — Descriptive statistics & Table 1

Deeper patterns: [references/03-descriptive-stats.md](references/03-descriptive-stats.md) — stratified Table 1 with SMDs, `asdoc` / `tabstat` / `balancetable`, correlation matrix with significance stars (`pwcorr, sig star(.05)`), histograms / kdensity by group, `xtline` for DID motivation, panel-coverage `xtdescribe`.

```stata
* 3a. Full-sample summary
local vars "log_wage age edu tenure training"
tabstat `vars', statistics(n mean sd min p25 p50 p75 max) columns(statistics)

* One-command Word/Excel output:
asdoc sum `vars', stat(N mean sd min median max) ///
    save(tables/table1_full.docx) replace

* 3b. Stratified Table 1 (treated vs control + t-tests + SMDs)
balancetable training age edu tenure female ///
    using "tables/table1_balance.tex", ///
    vce(cluster firm_id) replace ///
    varlabels pval

* Manual per-variable t-test + SMD:
foreach v of varlist age edu tenure {
    qui sum `v' if training == 1
    local m1 = r(mean); local sd1 = r(sd); local n1 = r(N)
    qui sum `v' if training == 0
    local m0 = r(mean); local sd0 = r(sd); local n0 = r(N)
    local smd = (`m1' - `m0') / sqrt((`sd1'^2 + `sd0'^2)/2)
    ttest `v', by(training)
    display "`v': Δ=" %7.3f (

…(truncated)