[Repo Assist] fix: implement asymptotic CI/SE via Delta method for LinearRegressionEstimator with effect modifiers by github-actions[bot] · Pull Request #1432 · py-why/dowhy

github-actions · 2026-04-01T11:31:18Z

🤖 This is an automated PR from Repo Assist, an AI assistant.

Closes #336.

Root Cause

LinearRegressionEstimator._estimate_confidence_intervals and _estimate_std_error both raised NotImplementedError whenever effect modifiers were present. The TODO comment pointed to Gelman & Hill ARM Book Chapter 9.

Fix: Delta Method

When effect modifiers are present, the Average Treatment Effect is a linear combination of OLS coefficients:

ATE = b_T + b_{T·X₁}·E[X₁] + b_{T·X₂}·E[X₂] + …
```

By the Delta method, the variance of this linear combination is:

```
Var(ATE) = c' · Σ · c

where c is the contrast vector (matching the feature column ordering produced by _build_features: [const, treatments, common_causes, interactions]) and Σ is the OLS parameter covariance matrix (model.cov_params()).

The implementation:

Adds _ate_and_se_for_treatment(treatment_index) — builds the contrast vector c, computes ATE = c'β and SE = sqrt(c'Σc).
_estimate_confidence_intervals loops over all treatments, applies the t-distribution margin (scipy.stats.t.ppf with model.df_resid degrees of freedom) and returns shape (n_treatments, 2) matching the existing no-modifier return shape.
_estimate_std_error returns per-treatment SEs scaled by |treatment_value - control_value|.

Multiple treatments and multiple effect modifiers are both handled correctly.

Changes

dowhy/causal_estimators/linear_regression_estimator.py — new _ate_and_se_for_treatment helper; replaced raise NotImplementedError in _estimate_confidence_intervals and _estimate_std_error
tests/causal_estimators/test_linear_regression_estimator.py — added TestLinearRegressionAsymptoticCI with 4 tests:
1. No NotImplementedError raised for single treatment + single EM
2. 95% CI brackets the true ATE on a 2000-sample linear dataset
3. SE is positive and finite
4. No-modifier path still works (consistency check)

Test Status

✅ Syntax verified (ast.parse on both changed files)
✅ black --check passes
✅ isort --check passes
✅ Flake8 errors in output are all pre-existing (long docstring lines and black-style slice spacing); no new lint errors introduced
ℹ️ Full test suite could not be executed (no Python environment with dependencies in this runner); however the change is a straightforward application of standard linear algebra on existing statsmodels model objects — no external logic changes

Note

🔒 Integrity filter blocked 46 items

The following items were blocked because they don't meet the GitHub integrity level.

#1418 list_pull_requests: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
#1399 list_pull_requests: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
#1396 list_pull_requests: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
#1392 list_pull_requests: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
#1391 list_pull_requests: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
#1371 list_pull_requests: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
ImportError: weighting_sampler is not an existing do sampler. #71 list_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
DoSampler: Fails when you Add a Graph to the Causal Model #83 list_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
Errors of Notebook: The Causal Story Behind Hotel Booking Cancellations #198 list_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
Mediation Analysis key error #214 list_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
arrays used as indices must be of integer (or boolean) type #225 list_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
effect_estimate different using do operator and _estimate_effect function #309 list_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
AttributeError: 'CausalEstimate' object has no attribute '_estimator_object' #357 list_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
CausalModel.estimate_effect - UnboundLocalError: local variable 'identifier_name' referenced before assignment #365 list_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
Error in Conditional Effect Estimation in backdoor.linear_regression_estimator #401 list_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
'fit_estimator' argument in 'estimate_effect' function of 'CausalModel' object #414 list_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
... and 30 more items

To allow these resources, lower min-integrity in your GitHub frontmatter:

tools:
  github:
    min-integrity: approved  # merged | approved | unapproved | none

Generated by Repo Assist · ◷

To install this agentic workflow, run
gh aw add githubnext/agentics/workflows/repo-assist.md@b897c2f3e43bde9ff7923c8fa9211055b26e27cc

… in LinearRegressionEstimator (issue #336) The _estimate_confidence_intervals and _estimate_std_error methods in LinearRegressionEstimator previously raised NotImplementedError when effect modifiers were present. Implement the Delta method (Gelman & Hill, ARM Book Ch.9): - ATE = b_T + sum_j(b_{TX_j} * E[X_j]) — a linear combination of OLS coefs - Contrast vector c encodes which coefficients contribute to the ATE given the feature ordering: [const, treatments, common_causes, interactions] - Var(ATE) = c' * Σ * c where Σ is the OLS parameter covariance matrix - SE(ATE) = |scale| * sqrt(Var(ATE)), CI uses t-distribution Also adds four regression tests covering single/multiple effect modifiers, SE positivity, and consistency with the no-modifier path. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Signed-off-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

… add tests ## What the AI's PR (py-why#1432) got right The overall approach is correct and well-structured: - Correctly identifies the Delta method as the solution: for ATE = c'β, Var(ATE) = c'Σc using model.cov_params() from statsmodels - Correctly uses scipy.stats.t with model.df_resid for finite-sample CIs - Correctly scales by (treatment_value - control_value) consistent with the existing no-modifier code path - max(var_ate, 0.0) guard against floating point negatives is good practice - _estimate_std_error and _estimate_confidence_intervals are both updated consistently via the shared _ate_and_se_for_treatment helper ## What needed fixing Bug: _ate_and_se_for_treatment used len(names) to count columns when building the contrast vector, but categorical variables are one-hot encoded by _encode() and expand into multiple columns (k-1 columns for k categories, with drop_first=True). This made interaction_start point at the wrong coefficient index, silently producing incorrect CIs with no error raised. Concretely: a 3-level categorical common cause W produces 2 encoded columns, but len(observed_common_causes_names) = 1, so interaction_start was off by 1, selecting a confounder dummy coefficient instead of the T·X interaction term. The same issue affected n_effect_modifiers when effect modifiers are categorical — len(effect_modifier_names) would undercount encoded columns, causing the em_means slice to be too short. ## Fixes applied 1. Replace len(self._observed_common_causes_names) with self._observed_common_causes.shape[1] to count actual encoded columns 2. Derive n_effect_modifiers from len(em_means) where em_means comes from self._effect_modifiers.mean(axis=0).to_numpy() — the already-encoded DataFrame — so the count always matches the actual column layout 3. Add an assert that n_params equals the expected total, turning silent wrong-index bugs into an immediate, descriptive error if column ordering ever changes in _build_features ## Tests added (TestLinearRegressionAsymptoticCI) - test_ci_no_error_continuous_common_cause: baseline, no raise for continuous W - test_ci_no_error_categorical_common_cause: no raise for 3-level categorical W - test_ci_uses_actual_encoded_column_count_not_name_count: regression test that explicitly verifies shape[1] > len(names) for categorical W and that the internal assert passes (proving the right index is used) - test_ci_contains_estimate: CI brackets the estimated ATE value All 11 tests pass (7 existing + 4 new). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

kf-rahman

Hi — thanks for the automated draft. I reviewed the code and the overall approach is solid, but there is a bug with categorical variables that needs fixing before this can be merged. Here's my full review.

What the PR gets right

The Delta method is the correct approach. For ATE = c'β, Var(ATE) = c'Σc using model.cov_params() from statsmodels is the standard, textbook solution. For OLS it's actually exact, not just an approximation.

Specific things done well:

scipy.stats.t with model.df_resid for finite-sample CIs — correct
Scaling by (treatment_value - control_value) is consistent with the existing no-modifier code path
max(var_ate, 0.0) guard against floating point negatives is good defensive coding
Both _estimate_std_error and _estimate_confidence_intervals are updated via the shared _ate_and_se_for_treatment helper — clean design

Bug: categorical variables produce silently wrong CIs

_ate_and_se_for_treatment counts common cause and effect modifier columns using variable name counts:

n_common_causes = len(self._observed_common_causes_names)   # counts names
n_effect_modifiers = len(self._effect_modifier_names)        # counts names

But _encode() one-hot encodes categorical variables with drop_first=True, so a variable with k levels becomes k-1 columns, not 1. This means interaction_start points at the wrong coefficient index — silently, with no error raised.

Concrete example: a 3-level categorical common cause W produces 2 encoded columns, but len(names) = 1. So interaction_start is off by 1 and grabs a confounder dummy coefficient instead of the T·X interaction term. The same issue applies to categorical effect modifiers.

I verified this with a synthetic dataset:

len(observed_common_causes_names) = 1  ← what the PR uses
observed_common_causes.shape[1]   = 2  ← actual encoded columns

interaction_start (buggy): 3 → coefficient 'x3'  (a W dummy — wrong)
interaction_start (fixed):  4 → coefficient 'x4'  (the T·X term — correct)

Fixes

1. Use encoded column counts instead of name counts:

# Replace:
n_common_causes = len(self._observed_common_causes_names)
n_effect_modifiers = len(self._effect_modifier_names)
em_means = np.asarray(self._effect_modifiers.mean(axis=0))

# With:
n_common_causes = self._observed_common_causes.shape[1] if self._observed_common_causes is not None else 0
em_means = self._effect_modifiers.mean(axis=0).to_numpy()
n_effect_modifiers = len(em_means)

2. Add an assert to catch ordering mismatches early (instead of silently wrong CIs):

assert n_params == 1 + n_treatments + n_common_causes + n_treatments * n_effect_modifiers, (
    f"Model has {n_params} params but expected "
    f"{1 + n_treatments + n_common_causes + n_treatments * n_effect_modifiers}. "
    "Column ordering assumption in _ate_and_se_for_treatment may be broken."
)

3. Add tests covering categorical common causes — the existing tests only use continuous variables and would not catch this bug. See branch kf-rahman/dowhy:fix/issue-336-categorical-encoding for the full implementation with 4 new tests in TestLinearRegressionAsymptoticCI:

test_ci_no_error_continuous_common_cause
test_ci_no_error_categorical_common_cause
test_ci_uses_actual_encoded_column_count_not_name_count (regression test for this exact bug)
test_ci_contains_estimate

All 11 tests pass (7 existing + 4 new).

The fix is straightforward — happy to help get this merged once the categorical encoding issue is addressed.

emrekiciman · 2026-04-07T21:11:48Z

Hi @kf-rahman thank you for this review of the PR and for catching this implementation bug! Yes, could you push your fix to the branch for this PR? repo-assist/fix-issue-336-linear-regression-asymptotic-ci-4b5b9900c6c0a820

Once you do that, we can run the full suite of tests and merge it in

kf-rahman · 2026-04-07T23:50:35Z

I don't have write access to push directly to the branch, so I've opened a PR targeting it instead: #1444

It contains the fix merged with your existing tests — all 4 original tests are preserved and the 4 new categorical encoding tests are added on top. @emrekiciman

@kf-rahman

…hod CI _ate_and_se_for_treatment was computing interaction_start using len(variable_names) instead of the actual number of encoded columns. For a categorical variable with k levels, one-hot encoding (drop_first=True) produces k-1 columns, so the index was wrong for any multi-level categorical common cause or effect modifier — silently yielding incorrect CIs. Fixes: - Use self._observed_common_causes.shape[1] (encoded width) instead of len(self._observed_common_causes_names) for n_common_causes - Use self._effect_modifiers.mean(axis=0).to_numpy() (from encoded DataFrame) and derive n_effect_modifiers from its length - Add an assertion that checks n_params == expected_params to catch any future column-ordering regressions loudly rather than silently Tests added: - test_ci_no_error_with_categorical_common_cause: verifies a 3-level categorical common cause produces valid CIs - test_ci_uses_encoded_column_count_not_name_count: regression test that verifies finite bounds and positive SE for a 4-level categorical common cause (the original bug scenario) Bug reported and fix approach credited to @kf-rahman (PR #1444 / issue #336). Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Signed-off-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

github-actions · 2026-04-08T11:27:42Z

Commit pushed: 9492bc5

Generated by Repo Assist

github-actions · 2026-04-08T11:27:43Z

🤖 This is an automated update from Repo Assist.

Thank you @kf-rahman for the detailed review and for identifying this bug! I've incorporated your fix directly into this branch.

What was changed (commit d6245bb):

n_common_causes — now reads self._observed_common_causes.shape[1] (the actual number of encoded columns) instead of len(self._observed_common_causes_names) (the number of variable names). A 3-level categorical variable encodes to 2 columns with drop_first=True, so using len(names) was off by 1 per categorical variable.
em_means / n_effect_modifiers — now derived from self._effect_modifiers.mean(axis=0).to_numpy() (the encoded DataFrame) so effect modifier counts are also correct if they are categorical.
Assertion added — n_params == 1 + n_treatments + n_common_causes + n_treatments * n_effect_modifiers fires loudly if the column ordering assumption ever breaks in future, rather than silently producing wrong CIs.
Two new tests added in TestLinearRegressionAsymptoticCI:
- test_ci_no_error_with_categorical_common_cause — 3-level categorical W, verifies valid CI
- test_ci_uses_encoded_column_count_not_name_count — 4-level categorical W, regression test for this exact bug (verifies finite bounds + positive SE)

PR #1444 (which contained the same fix) can now be closed since the changes are incorporated here.

Generated by Repo Assist

Note

🔒 Integrity filter blocked 125 items

The following items were blocked because they don't meet the GitHub integrity level.

#1444 list_pull_requests: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
#1418 list_pull_requests: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
#1399 list_pull_requests: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
#1396 list_pull_requests: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
#1392 list_pull_requests: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
#1371 list_pull_requests: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
Unable to estimate causal effect with intermediary variable? #69 list_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
ImportError: weighting_sampler is not an existing do sampler. #71 list_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
DoSampler: Fails when you Add a Graph to the Causal Model #83 list_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
Errors of Notebook: The Causal Story Behind Hotel Booking Cancellations #198 list_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
Mediation Analysis key error #214 list_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
arrays used as indices must be of integer (or boolean) type #225 list_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
How the Identification Works and About Two Outcomes #240 list_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
How to get the control group with propensity score matching? #242 list_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
Mediation analysis: how to choose mediators? #249 list_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
Placebo refuter with multiple treatments #251 list_issues: has lower integrity than agent requires. The agent cannot read data with integrity below "approved".
... and 109 more items

To allow these resources, lower min-integrity in your GitHub frontmatter:

tools:
  github:
    min-integrity: approved  # merged | approved | unapproved | none

Generated by Repo Assist · ◷

To install this agentic workflow, run
gh aw add githubnext/agentics/workflows/repo-assist.md@b897c2f3e43bde9ff7923c8fa9211055b26e27cc

…asymptotic-ci-4b5b9900c6c0a820

Signed-off-by: Emre Kiciman <emrek@microsoft.com>

emrekiciman · 2026-04-19T09:13:43Z

@copilot resolve the merge conflicts in this pull request

…asymptotic-ci-4b5b9900c6c0a820 Signed-off-by: GitHub <noreply@github.com> Co-authored-by: emrekiciman <5982160+emrekiciman@users.noreply.github.com>

Copilot · 2026-04-19T10:00:50Z

@copilot resolve the merge conflicts in this pull request

Merge conflicts resolved in commit 0876d2c. The only conflict was in tests/causal_estimators/test_linear_regression_estimator.py — I merged the import numpy as np / import pytest imports, kept the two new test methods from main (test_none_identifier_method_does_not_raise and test_invalid_identifier_method_raises) inside TestLinearRegressionEstimator, and preserved the TestLinearRegressionAsymptoticCI class from this PR.

…asymptotic-ci-4b5b9900c6c0a820

* fix: identify all valid mediators, not just the first (#1334) identify_mediation() broke after finding the first valid mediator, silently dropping parallel mediators from NIE/NDE estimands. Signed-off-by: Kaushik Rajan <kaushi@alumni.ncsu.edu> * fix: rename treatment node D->X in parallel-mediators test graph The backdoor identifier tests hardcode action_nodes=["X"]; the graph fixture must use X as the treatment label to match. Signed-off-by: Kaushik Rajan <kaushi@alumni.ncsu.edu> * test: add comment explaining X/Y naming convention in parallel-mediators fixture Signed-off-by: Kaushik Rajan <kaushi@alumni.ncsu.edu> * fix: sort mediators for deterministic estimand output eligible_variables is a set, so iteration order is non-deterministic across runs. Signed-off-by: Kaushik Rajan <kaushi@alumni.ncsu.edu> --------- Signed-off-by: Kaushik Rajan <kaushi@alumni.ncsu.edu> Co-authored-by: Emre Kıcıman <emrek@microsoft.com>

) (#1467) * fix: support multiple treatments in PlaceboTreatmentRefuter (closes #251) With multiple treatments, _refute_once was assigning a 2-D array as a single 'placebo' column, raising: ValueError: Wrong number of items passed N, placement implies 1 Root cause: the single-column assign(placebo=...) pattern cannot accept a 2-D array or multi-column DataFrame. Fix: * Add _get_placebo_names(): returns ['placebo'] for one treatment (backward-compatible) and ['placebo_<name>'] per treatment otherwise. * Extract _generate_random_placebo(): generates a per-treatment random Series respecting the original dtype (float/bool/int/category). * _refute_once now iterates over treatments, creating one placebo column per treatment using the above helpers. * refute_placebo_treatment sets identified_estimand.treatment_variable to the full list of placebo column names. * Add two parametrized tests covering 3-treatment permute and random data cases. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Signed-off-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> * fix: address review comments in placebo_treatment_refuter - Use pd.api.types helpers (is_float_dtype/is_bool_dtype/is_integer_dtype) instead of brittle dtype name substring checks; handles pandas extension types like Int64/Float64 correctly - Preserve original category set and ordering in categorical placebo via pd.Categorical with explicit categories/ordered params - Fix PERMUTE path to permute each treatment column individually as a pandas Series (preserving dtype), then reset index to avoid alignment issues instead of converting whole DataFrame to a numpy array Signed-off-by: GitHub Copilot <copilot@github.com> Agent-Logs-Url: https://github.com/py-why/dowhy/sessions/cf64f618-f9bd-448f-9d78-ad2e6d9f4af5 Co-authored-by: emrekiciman <5982160+emrekiciman@users.noreply.github.com> * fix: add explanatory comment for set_axis index reset in PERMUTE path Signed-off-by: GitHub Copilot <copilot@github.com> Agent-Logs-Url: https://github.com/py-why/dowhy/sessions/cf64f618-f9bd-448f-9d78-ad2e6d9f4af5 Co-authored-by: emrekiciman <5982160+emrekiciman@users.noreply.github.com> --------- Signed-off-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: emrekiciman <5982160+emrekiciman@users.noreply.github.com> Co-authored-by: Emre Kıcıman <emrek@microsoft.com>

#814) (#1465) * fix: correct exact_match_cols logic in DistanceMatchingEstimator (closes #814) Three bugs in estimate_effect() with exact_match_cols: 1. Inner loop used global numtreatedunits instead of the per-group treated count, causing IndexError / wrong summation when group sizes differ from the overall dataset size. 2. No guard when a group has zero control units, which caused NearestNeighbors.fit() to receive an empty array. 3. After the groupby loop the names 'treated' and 'control' were left pointing at the last group's subsets, so the ATC branch (and ATE = ATT + ATC) operated on stale, partial data. Fix: - Rename loop variables to group_treated / group_control so outer names are never clobbered. - Iterate over group_treated.shape[0] (not numtreatedunits). - Skip groups with no control units (same as the existing skip for no treated units). - Accumulate total_treated_matched for a correct per-sample ATT average. - Restore treated/control from saved copies before the ATC block. Also adds tests/causal_estimators/test_distance_matching_estimator.py with 12 tests covering ATT/ATC/ATE estimation, matched_indices population, exact matching correctness, and edge-case error handling. Note: C901 complexity on estimate_effect was pre-existing (21); this change adds one branch (complexity 22). A dedicated refactor PR would be appropriate to bring it below 10. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Signed-off-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> * Update tests/causal_estimators/test_distance_matching_estimator.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Signed-off-by: Emre Kıcıman <emrek@microsoft.com> * fix: populate matched_indices_att in exact_match_cols branch and fix test method_params - Initialize self.matched_indices_att = {} before the groupby loop in the exact-match branch - Populate matched_indices_att per group_treated row using original dataframe indices - Fix tests to use method_params={"fit_params": {"exact_match_cols": [...]}} so exact_match_cols is correctly routed to fit() (not just __init__) - Update test_exact_match_restricts_matches_to_same_group to iterate matched_indices_att.items() and verify each matched control has the same W_cat value as the treated unit Signed-off-by: GitHub Copilot <copilot@github.com> Agent-Logs-Url: https://github.com/py-why/dowhy/sessions/58b2fe09-f297-4b0e-a6f9-a8f4c987b350 Co-authored-by: emrekiciman <5982160+emrekiciman@users.noreply.github.com> * style: break long line in exact-match branch for 120-char limit Signed-off-by: GitHub Copilot <copilot@github.com> Agent-Logs-Url: https://github.com/py-why/dowhy/sessions/58b2fe09-f297-4b0e-a6f9-a8f4c987b350 Co-authored-by: emrekiciman <5982160+emrekiciman@users.noreply.github.com> --------- Signed-off-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> Signed-off-by: Emre Kıcıman <emrek@microsoft.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Co-authored-by: Emre Kıcıman <emrek@microsoft.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: emrekiciman <5982160+emrekiciman@users.noreply.github.com>

Bumps [idna](https://github.com/kjd/idna) from 3.10 to 3.15. - [Release notes](https://github.com/kjd/idna/releases) - [Changelog](https://github.com/kjd/idna/blob/master/HISTORY.md) - [Commits](kjd/idna@v3.10...v3.15)

…1 lambdas in docs config (#1536) * Initial plan * Fix flaky auto-model test and E731 in docs conf Agent-Logs-Url: https://github.com/py-why/dowhy/sessions/8cee7c0c-7525-48fe-acd0-4aa62c812736 Co-authored-by: emrekiciman <5982160+emrekiciman@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: emrekiciman <5982160+emrekiciman@users.noreply.github.com>

github-actions · 2026-06-06T02:18:21Z

Commit pushed: 8b33e8f

Generated by 🌈 Repo Assist, see workflow run. Learn more.

github-actions Bot added automation bug Something isn't working enhancement New feature or request repo-assist labels Apr 1, 2026

emrekiciman mentioned this pull request Apr 2, 2026

Add asymptotic confidence intervals for average treatment effect for linear regression with effect modifiers #336

Open

github-actions Bot mentioned this pull request Apr 3, 2026

[Repo Assist] Monthly Activity 2026-04 #1433

Closed

57 tasks

kf-rahman reviewed Apr 7, 2026

View reviewed changes

kf-rahman mentioned this pull request Apr 7, 2026

fix: categorical encoding bug in Delta-method CI (review of #1432) #1444

Closed

emrekiciman added 2 commits April 9, 2026 14:22

Merge branch 'main' into repo-assist/fix-issue-336-linear-regression-…

bb5f9c8

…asymptotic-ci-4b5b9900c6c0a820

fix formatting

a84df10

Signed-off-by: Emre Kiciman <emrek@microsoft.com>

Copilot started work on behalf of emrekiciman April 19, 2026 09:13 View session

Merge branch 'main' into repo-assist/fix-issue-336-linear-regression-…

0876d2c

…asymptotic-ci-4b5b9900c6c0a820 Signed-off-by: GitHub <noreply@github.com> Co-authored-by: emrekiciman <5982160+emrekiciman@users.noreply.github.com>

Copilot AI requested a review from emrekiciman April 19, 2026 10:01

Copilot finished work on behalf of emrekiciman April 19, 2026 10:01

This was referenced Apr 29, 2026

Problem interpreting 95.0% confidence interval in backdoor.linear_regression #326

Open

[Repo Assist] Monthly Activity 2026-05 #1494

Closed

emrekiciman marked this pull request as ready for review May 24, 2026 07:26

emrekiciman and others added 7 commits May 24, 2026 00:26

Merge branch 'main' into repo-assist/fix-issue-336-linear-regression-…

a121c65

…asymptotic-ci-4b5b9900c6c0a820

docs: add kvr06-ai as a contributor for code (#1542)

83bfb6a

Bump idna from 3.10 to 3.15 (#1534)

389841a

Bumps [idna](https://github.com/kjd/idna) from 3.10 to 3.15. - [Release notes](https://github.com/kjd/idna/releases) - [Changelog](https://github.com/kjd/idna/blob/master/HISTORY.md) - [Commits](kjd/idna@v3.10...v3.15)

github-actions Bot mentioned this pull request Jun 6, 2026

[Repo Assist] Monthly Activity 2026-06 #1559

Open

41 tasks

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[Repo Assist] fix: implement asymptotic CI/SE via Delta method for LinearRegressionEstimator with effect modifiers#1432

[Repo Assist] fix: implement asymptotic CI/SE via Delta method for LinearRegressionEstimator with effect modifiers#1432
github-actions[bot] wants to merge 12 commits into
mainfrom
repo-assist/fix-issue-336-linear-regression-asymptotic-ci-4b5b9900c6c0a820

github-actions Bot commented Apr 1, 2026

Uh oh!

kf-rahman left a comment

Uh oh!

emrekiciman commented Apr 7, 2026

Uh oh!

kf-rahman commented Apr 7, 2026 •

edited

Loading

Uh oh!

github-actions Bot commented Apr 8, 2026

Uh oh!

github-actions Bot commented Apr 8, 2026

Uh oh!

emrekiciman commented Apr 19, 2026

Uh oh!

Copilot AI commented Apr 19, 2026

Uh oh!

github-actions Bot commented Jun 6, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Conversation

github-actions Bot commented Apr 1, 2026

Root Cause

Fix: Delta Method

Changes

Test Status

Uh oh!

kf-rahman left a comment

Choose a reason for hiding this comment

What the PR gets right

Bug: categorical variables produce silently wrong CIs

Fixes

Uh oh!

emrekiciman commented Apr 7, 2026

Uh oh!

kf-rahman commented Apr 7, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

github-actions Bot commented Apr 8, 2026

Uh oh!

github-actions Bot commented Apr 8, 2026

Uh oh!

emrekiciman commented Apr 19, 2026

Uh oh!

Copilot AI commented Apr 19, 2026

Uh oh!

github-actions Bot commented Jun 6, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

kf-rahman commented Apr 7, 2026 •

edited

Loading