Research map / Probabilistic and scientific modeling / Treatment effects
Valid Causal Inference with (Some) Invalid Instruments
Jason S Hartford, Victor Veitch, Dhanya Sridhar, Kevin Leyton-Brown
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Aggregate per-instrument DeepIV estimates by the modal interval | DeepIV ensemble · Biased demand simulation with invalid instruments | mean squared error | Improved |
| Use the mean of per-instrument DeepIV estimates instead of the modal interval | DeepIV ensemble · Mendelian randomization simulation | average absolute CATE bias | Hurt |
| Treat all candidate instruments as valid rather than filtering by the modal interval | DeepIV · Mendelian randomization simulation with invalid instruments | average absolute CATE bias | Hurt |
| Use the modal interval with V set to the true number of valid instruments (ablation) | ModeIV · Biased demand simulation | mean squared error | Improved |
| Set V too small (ablation) | ModeIV with only 5 valid instruments · Biased demand simulation | mean squared error | Hurt |
| Use more conservative choices of V (ablation) | ModeIV · Biased demand simulation | mean squared error | No clear effect |
| Use ModeIV instead of oracle DeepIV on known valid instruments | DeepIV · Mendelian randomization simulation | average absolute CATE bias: 0.035 vs 0.037 (50% valid); 0.024 vs 0.032 (100% valid) | Hurt |
Closest papers by meaning
- Conditional Instrumental Variable Regression with Representation Learning for Causal Inference (ICLR 2024 · similarity 0.90)
- Data-Driven Selection of Instrumental Variables for Additive Nonlinear, Constant Effects Models (ICML 2025 · similarity 0.90)
- Learning Representations of Instruments for Partial Identification of Treatment Effects (ICML 2025 · similarity 0.89)
- Conditional Common Entropy for Instrumental Variable Testing and Partial Identification (ICML 2024 · similarity 0.88)
- Estimating Heterogeneous Treatment Effects by Combining Weak Instruments and Observational Data (NeurIPS 2024 · similarity 0.88)
- An Analysis of Causal Effect Estimation using Outcome Invariant Data Augmentation (NeurIPS 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
