Method library WORKFLOW / 037

Research workflow/4 steps

Goodman-Bacon decomposition: what your TWFE estimate is averaging (bacondecomp)

@bacondecomp ✓ P D · Jun 29, 2026 · 901 views

Source bacondecomp — Flack; Goodman-Bacon (2021)

@misc{bacondecomp,
  title        = {bacondecomp},
  author       = {2021},
  howpublished = {\url{https://github.com/evanjflack/bacondecomp}},
  note         = {Software / documentation}
}

In the margins · Peer notes@avg_treatment · Great diagnostic, but it's a diagnosis not a cure — pair it with Callaway-Sant'Anna or did2s when the bad comparis… 2

The method workspace

Follow the analysis.

Select a node to explore the method

Method mapInput → 4 steps → output

START WITHInput data

ARRIVE ATResults

Read step 01

Inside the methodReasoning, equations & implementation

Data prep

A staggered-adoption panel

Step notesField note & discussion1

Data preparation — shapes the raw inputs into what the estimator expects.

What happens here

Units switch treatment on at different dates. The TWFE coefficient you'd normally report hides a lot of structure.

Formula

y_{it}=\alpha_i+\gamma_t+\beta^{TWFE}D_{it}+\varepsilon_{it}

Reads fromNot specified Feeds intoNot specified

Key code

# unit, year, y, treated (0/1, turns on and stays on)

Reference / docs ↗

Discussion on this step (0)

StatsOtterDiscussion starter · Editorial note

Before using this step, make its assumptions and its output explicit. A useful peer note explains what you would check, what could go wrong, or what would change your interpretation.

Questions to explore

Which assumption matters most here, and what evidence could challenge it?
What would you check before passing this output to the next step?

Peer discussion

Bring your experience, a question, or a different perspective.

Diagnostic / pre-tests

Decompose into 2×2 comparisons

Step notesField note & discussion1

A pre-flight check — run this before trusting any estimate downstream.

What happens here

Every pair of timing groups forms a 2×2 DiD; TWFE is their variance-weighted average.

Formula

\hat\beta^{TWFE}=\textstyle\sum_k s_k\,\hat\beta_k^{2\times2},\qquad \textstyle\sum_k s_k=1

Reads fromNot specified Feeds intoNot specified

Key code

df_bacon <- bacon(y ~ treated, data = panel,
                  id_var = 'unit', time_var = 'year')

Reference / docs ↗

Discussion on this step (0)

StatsOtterDiscussion starter · Editorial note

Before using this step, make its assumptions and its output explicit. A useful peer note explains what you would check, what could go wrong, or what would change your interpretation.

Questions to explore

Which assumption matters most here, and what evidence could challenge it?
What would you check before passing this output to the next step?

Peer discussion

Bring your experience, a question, or a different perspective.

Robustness check

Spot the forbidden comparisons

Step notesField note & discussion1

A robustness check — does the headline result survive a different lens?

What happens here

'Later vs earlier treated' uses already-treated units as controls — under dynamic effects this term is biased and can carry negative weight.

Formula

s_k\ \propto\ n_k\,\bar D_k\,(1-\bar D_k)\quad(\text{treatment-variance weights})

Reads fromNot specified Feeds intoNot specified

Key code

library(ggplot2)
ggplot(df_bacon, aes(weight, estimate, color = type)) + geom_point()

Reference / docs ↗

Discussion on this step (0)

StatsOtterDiscussion starter · Editorial note

Before using this step, make its assumptions and its output explicit. A useful peer note explains what you would check, what could go wrong, or what would change your interpretation.

Questions to explore

Which assumption matters most here, and what evidence could challenge it?
What would you check before passing this output to the next step?

Peer discussion

Bring your experience, a question, or a different perspective.

Reporting

Read β as a weighted average

Step notesField note & discussion1

Reporting — turn the numbers into a figure or table a reader can act on.

What happens here

If the dangerous comparisons carry real weight, prefer a modern estimator (Callaway-Sant'Anna, did2s) over plain TWFE.

Formula

\hat\beta^{TWFE}=\mathbb E_S[\hat\beta_k]\ \Rightarrow\ \text{trustworthy only if the weights are}

Reads fromNot specified Feeds intoNot specified

Key code

weighted.mean(df_bacon$estimate, df_bacon$weight)

Reference / docs ↗

Discussion on this step (0)

StatsOtterDiscussion starter · Editorial note

Before using this step, make its assumptions and its output explicit. A useful peer note explains what you would check, what could go wrong, or what would change your interpretation.

Questions to explore

Which assumption matters most here, and what evidence could challenge it?
What would you check before passing this output to the next step?

Peer discussion

Bring your experience, a question, or a different perspective.

Data contract

Inputs & data

A staggered-adoption panel: units adopting treatment at different times, with a binary treatment indicator.

Show data format & exampleHide example

Format — long panel: unit, time, outcome y, treatment treated (0/1, absorbing).

library(bacondecomp)
df_bacon <- bacon(y ~ treated, data = panel,
                  id_var = 'unit', time_var = 'year')

Read the evidence

Results & interpretation

1 figure Workflow discussion 2

01FigureGoodman-Bacon decomposition: each 2×2 DiD comparison's estimate vs. its TWFE weight, split by type — the 'later vs earlier treated' triangles are the risky ones.

Figures reproduced from bacondecomp — Flack; Goodman-Bacon (2021) — unofficial community showcase; all credit to the original authors.

Context & interpretation

⚠️ Unofficial community showcase of bacondecomp. Not affiliated with the authors; all credit to them.

A two-way fixed-effects DiD is a weighted average of all possible 2×2 comparisons — including 'forbidden' ones that use already-treated units as controls. This shows you the weights.

Peer notes

Discuss the workflow (2)

2

@did_master · Jun 29, 2026

Every staggered-DiD paper should print this plot. Once you see the 'later vs earlier treated' weight, you can't unsee the TWFE problem.
1

@avg_treatment · Jun 29, 2026

Great diagnostic, but it's a diagnosis not a cure — pair it with Callaway-Sant'Anna or did2s when the bad comparisons carry weight.