User guide

• 1. The basics of double/debiased machine learning
  • 1.1. Data generating process
  • 1.2. Regularization bias in simple ML-approaches
  • 1.3. Overcoming regularization bias by orthogonalization
  • 1.4. Sample splitting to remove bias induced by overfitting
  • 1.5. Double/debiased machine learning
  • 1.6. Partialling out score
  • 1.7. References
• 2. The data-backend DoubleMLData
  • 2.1. DoubleMLData from dataframes
  • 2.2. DoubleMLData from arrays and matrices
• 3. Models
  • 3.1. Partially linear regression model (PLR)
  • 3.2. Partially linear IV regression model (PLIV)
  • 3.3. Interactive regression model (IRM)
  • 3.4. Interactive IV model (IIVM)
• 4. Score functions
  • 4.1. Implementation of the score function and the estimate of the causal parameter
  • 4.2. Implemented Neyman orthogonal score functions
    • 4.2.1. Partially linear regression model (PLR)
    • 4.2.2. Partially linear IV regression model (PLIV)
    • 4.2.3. Interactive regression model (IRM)
    • 4.2.4. Interactive IV model (IIVM)
  • 4.3. Specifying alternative score functions via callables
• 5. Double machine learning algorithms
  • 5.1. Algorithm DML1
  • 5.2. Algorithm DML2
  • 5.3. Implementation of the double machine learning algorithms
• 6. Learners, hyperparameters and hyperparameter tuning
  • 6.1. Python: Learners and hyperparameters
    • 6.1.1. Minimum requirements for learners
    • 6.1.2. Specifying learners and set hyperparameters
    • 6.1.3. Hyperparameter tuning
  • 6.2. R: Learners and hyperparameters
    • 6.2.1. Minimum requirements for learners
    • 6.2.2. Specifying learners and set hyperparameters
    • 6.2.3. Using pipelines to construct learners
    • 6.2.4. Hyperparameter tuning
    • 6.2.5. Hyperparameter tuning with pipelines
• 7. Variance estimation and confidence intervals for a causal parameter of interest
  • 7.1. Variance estimation
• 8. Confidence bands and multiplier bootstrap for valid simultaneous inference
  • 8.1. Multiplier bootstrap and joint confidence intervals
  • 8.2. References
• 9. Sample-splitting, cross-fitting and repeated cross-fitting
  • 9.1. Cross-fitting with \(K\) folds
  • 9.2. Repeated cross-fitting with \(K\) folds and \(M\) repetition
  • 9.3. Externally provide a sample splitting / partition
  • 9.4. Sample-splitting without cross-fitting
  • 9.5. Estimate DML models without sample-splitting