under 7 different scenarios: 1. Null scenario: no effect of treatment 2. RCT scenario: treatment randomly assigned 3. Confounder-adjusted 4. Confounder-adjusted with instrument 5. Confounder-adjusted and subject to selection bias 6. Confounder-adjusted and subject to selection bias with instrument 7. Confounder-adjusted and subject to selection bias with instrument and common cause of instrument and outcome With scenario number 7 being what we believe to be closest to the truth. |