Causal Effect Estimation on 6-node graph (n=5000, 100 trials)
0Absolute BiasIIC
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| IICEdge=W2 → Y (conf.)2026.04 | 0 | 0.02 | |
| IICEdge=W3 → W2 (no conf.)2026.04 | 0 | 0.014 | |
| OLSEdge=W3 → W2 (no conf.)2026.04 | 0 | 0.014 | |
| IICEdge=T → Y (conf.)2026.04 | 0.001 | 0.02 | |
| 2SLSEdge=T → Y (conf.)2026.04 | 0.001 | 0.02 | |
| OLSEdge=Z → T (no conf.)2026.04 | 0.002 | 0.015 | |
| IICEdge=Z → T (no conf.)2026.04 | 0.003 | 0.017 | |
| 2SLSEdge=Z → T (no conf.)2026.04 | 0.003 | 0.017 | |
| IICEdge=W1 → Y (conf.)2026.04 | 0.003 | 0.019 | |
| OLSEdge=W1 → Y (conf.)2026.04 | 0.13 | 0.13 | |
| OLSEdge=W2 → Y (conf.)2026.04 | 0.168 | 0.168 | |
| OLSEdge=T → Y (conf.)2026.04 | 0.213 | 0.213 |