DoubleML 0.11.1

• Release highlight: Hyperparameter tuning with Optuna (by Jan Teichert-Kluge)

  • Implementation of tune_ml_models() method for DoubleML classes Py #368
  • Extended User Guide and Example Gallery Docs #260

• Maintenance package Py #372 Py #374 Py #377

• Maintenance documentation Docs #261 Docs #262

DoubleML 0.11.0

• Release highlight: Logistic Partially Linear Regression Model (by Julius Herzig)

  • Implementation via DoubleMLLPLR class (Py #365)
  • Extended User Guide and Example Gallery (Docs #253)

• Refactored data classes (by Jan Teichert-Kluge) (Py #338, Py #337, Py #336, Docs #251)

  • Integrated clusters into DoubleMLData class
  • Added model specific data backends:
    • DoubleMLPanelData
    • DoubleMLSSMData
    • DoubleMLRDDData
  • Data generators are placed into the corresponding submodules, e.g. from doubleml.plm.datasets import make_plr_CCDDHNR2018 (Py #331, Py #332)

• Updated nuisance tuning for DoubleMLSSM class (by Batuhan Tongarlak) (Py #352)

• Updated propensity score handling in irm and did models, via new PSProcessor class (Py #363, Docs #254)

• Added TabPFN example notebook (Docs #248, Docs #259)

• Maintenance package (Py #354, Py #355, Py #356, Py #357, Py #358, Py #359, Py #360, Py #361, Py #367, Py #367, Py #369, Py #370, Py #371)

• Maintenance documentation (Docs #249, Docs #250, Docs #252, Docs #255, Docs #256, Docs #257, Docs #258)

DoubleML 0.10.1

• Release highlight: Multi-Period Difference-in-Differences for Repeated Cross Sections

  • Implementation via DoubleMLDIDMulti class Py #330 Py #345
  • Extended User Guide and Example Gallery Docs #243

• Allow user defined bandwidth for RDFlex Py #343

• Maintenance package Py #327 Py #336

• Maintenance documentation Docs #241 Docs #242 Docs #244 Docs #245 Docs #246

DoubleML 0.10.0

• Release highlight: Multi-Period Difference-in-Differences for Panel Data

  • Implementation via DoubleMLDIDMulti class (Py #292, Py #315)
  • New doubleml.data submodule including DoubleMLData and DoubleMLPanelData classes (Py #292)
  • Extended User Guide and Example Gallery (Docs #224, Docs #233, Docs #237)

• Added Confidence sets which are robust to weak IVs: robust_confset() method for DoubleMLIIVM (added by Ezequiel Smucler and David Masip) (Py #318, Docs #234)

• Update sensitivity operations to improve sensitivity bounds (Py #295)

• Improve DoubleMLAPO nuisance estimation and update weighted score elements. Added example to compare DoubleMLIRM and DoubleMLAPO (Py #295, Py #297, Docs #220)

• Updated variance aggregation over repetitions via confidence intervals (Py #324, Docs #236)

• Added a separate package citation using CITATION.cff (Py #321)

• Update package formatting, linting and add pre-commit hooks (Py #288, Py #289, Py #294, Py #316)

• Maintenance package (Py #287, Py #288, Py #291, Py #319)

• Maintenance documentation (Docs #211, Docs #213, Docs #214, Docs #215, Docs #216, Docs #217, Docs #218, Docs #219, Docs #221, Docs #225, Docs #227, Docs #228, Docs #229, Docs #230, Docs #232, Docs #238, Docs #239)

DoubleML 0.9.3

• Fixed/Adapted unit tests that failed in the release of 0.9.2 to conda-forge. #208

DoubleML 0.9.2

• Make rdrobust optional for conda. Create pyproject.toml and remove setup.py for packaging #285 #286

• Maintenance package #284

• Maintenance documentation #205 #206 #207

DoubleML 0.9.1

• Release highlight: Regression Discontinuity Designs with Flexible Covariate Adjustment
  via RDFlex class (in cooperation with Claudia Noack and Tomasz Olma; see their paper) #276

• Add cov_type=HC0 and enable key-worded arguments to DoubleMLBLP #270 #271

• Update User Guide and Example Gallery #204

• Add AutoML example for tuning DoubleML estimators #199

• Maintenance package #268 #278 #279 #281 #282

• Maintenance documentation #201 #203

DoubleML 0.9.0

• Release highlight: Average potential outcomes for multiple discrete treatments
  via DoubleMLAPO and DoubleMLAPOS classes (proposed by Apoorva Lal) #245 #250

• Update User Guide and Example Gallery #188 #195

• Add sensitivity analysis to DoubleMLFramework #249

• Maintenance package #264 #265 #266

• Maintenance documentation #182 #184 #186 #193 #194 #196 #197

DoubleML 0.8.2

• API Update: Change nuisance evaluation for classifiers. The corresponding properties are renamed nuisance_loss instead of rmses #254 #184

• Add new example on sensitivity analysis #190

• Add a new example on DiD with DoubleML in R #178

• Enable set_sample_splitting for cluster data #255

• Update the make_confounded_irm_data data generating process #263

• Maintainance package #264

• Maintenance documentation #177 #180 #181 #187 #189