Method library WORKFLOW / 032

Research workflow/4 steps

Model, identify, estimate, refute — the DoWhy four-step recipe (DoWhy)

@dowhy ✓ P D · Jun 29, 2026 · 1.1k views

Source DoWhy — PyWhy / Microsoft (Sharma, Kiciman et al.)

@misc{dowhy,
  title        = {DoWhy},
  author       = {Sharma and Kiciman and others},
  howpublished = {\url{https://www.pywhy.org/dowhy/}},
  note         = {Software / documentation}
}

In the margins · Peer notes@rahul_nair · Encoding the DAG up front forces the awkward assumptions into the open. Wish more pipelines did this. 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

Model — encode the causal graph

Step notesField note & discussion1

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

What happens here

State the DAG over treatment, outcome, confounders and instruments. The assumptions go in up front, as a graph, not buried in a regression.

Formula

\tau=\mathbb{E}\big[Y\mid do(T{=}1)\big]-\mathbb{E}\big[Y\mid do(T{=}0)\big]

Reads fromNot specified Feeds intoNot specified

Key code

from dowhy import CausalModel
model = CausalModel(data=df, treatment='v0', outcome='y', graph=gml_graph)

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

Identify — apply the backdoor criterion

Step notesField note & discussion1

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

What happens here

DoWhy searches the graph for a valid adjustment set (backdoor), or an instrument/front-door, and returns the estimand symbolically — before touching the data.

Formula

\mathbb{E}[Y\mid do(T{=}t)]=\sum_{w}\mathbb{E}[Y\mid T{=}t,\,W{=}w]\,P(W{=}w)

Reads fromNot specified Feeds intoNot specified

Key code

estimand = model.identify_effect(proceed_when_unidentifiable=False)

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.

Estimation

Estimate — adjust for the backdoor set

Step notesField note & discussion1

The core estimate — where the causal quantity itself is computed.

What happens here

Plug in any estimator for the identified estimand: linear adjustment, propensity weighting/matching, or a DML/forest backend.

Formula

\hat\tau=\frac1n\sum_i\Big(\frac{T_iY_i}{\hat e(W_i)}-\frac{(1-T_i)Y_i}{1-\hat e(W_i)}\Big)

Reads fromNot specified Feeds intoNot specified

Key code

est = model.estimate_effect(estimand,
        method_name='backdoor.propensity_score_weighting')

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

Refute — placebo & unobserved-confounder tests

Step notesField note & discussion1

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

What happens here

The step that earns trust: a random common cause shouldn't change τ̂; a placebo (permuted) treatment should drive it to zero; subsetting shouldn't move it much.

Formula

\hat\tau_{\text{rand.\ cause}}\approx\hat\tau,\qquad \hat\tau_{\text{placebo}}\approx 0

Reads fromNot specified Feeds intoNot specified

Key code

model.refute_estimate(estimand, est,
        method_name='placebo_treatment_refuter')

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 dataset plus a causal graph (DAG) naming treatment, outcome, confounders and any instruments — the assumptions you're willing to defend.

Show data format & exampleHide example

Format — a tidy table together with a causal graph (DOT/GML) over treatment v0, outcome y and confounders W*.

import dowhy.datasets
d = dowhy.datasets.linear_dataset(
        beta=10, num_common_causes=5, num_instruments=1, num_samples=1000)
# d['df']: v0 (treatment), y (outcome), W0..W4 (confounders), X0

Read the evidence

Results & interpretation

2 figures Workflow discussion 2

01FigureThe assumed causal graph: confounders W0–W4 point into both the treatment v0 and the outcome y; DoWhy reads identifiability straight off this DAG.

02FigureRefutation — 'effect of an unobserved common cause': how the estimate shifts as a hypothetical confounder's strength on treatment and outcome grows.

Figures reproduced from DoWhy — PyWhy / Microsoft (Sharma, Kiciman et al.) — unofficial community showcase; all credit to the original authors.

Context & interpretation

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

Make your assumptions explicit: draw a causal graph, identify the estimand by the backdoor criterion, estimate it, then actively try to refute it with placebo and confounding tests.

Peer notes

Discuss the workflow (2)

2

@aipw_amir · Jun 29, 2026

The refute step is what sells DoWhy to me — placebo and random-common-cause as a default habit, not an afterthought.
1

@rahul_nair · Jun 29, 2026

Encoding the DAG up front forces the awkward assumptions into the open. Wish more pipelines did this.

1

@honest_hugo · Jun 29, 2026

Exactly — identification before estimation. The backdoor set is a modelling decision, not a tuning knob.