1 / 26

Causal Model Ying Nian Wu UCLA Department of Statistics July 13, 2007 IPAM Summer School

Causal Model Ying Nian Wu UCLA Department of Statistics July 13, 2007 IPAM Summer School. Observational study --- observed relationship may not be cause-effect Example: people who sleep 7 hours report better health. sleep 7 hrs (vs 8 hrs). health. health. sleep 7 hrs (vs 8 hrs).

rozene
Download Presentation

Causal Model Ying Nian Wu UCLA Department of Statistics July 13, 2007 IPAM Summer School

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Causal Model Ying Nian Wu UCLA Department ofStatistics July 13, 2007 IPAM Summer School

  2. Observational study --- observed relationship may not be cause-effect Example: people who sleep 7 hours report better health sleep 7 hrs (vs 8 hrs) health health sleep 7 hrs (vs 8 hrs)

  3. Example: people who smoke cigarette have better health than people who smoke pipe cigarette (vs pipe) health

  4. Confounding variable age cigarette (vs pipe) health cigarette (vs pipe) health

  5. Donald B. Rubin EM algorithm – Dempster, Laird, Rubin Missing data: ignorability multiple imputation Little & Rubin book Bayesian statistics: foundations and applications Gelman et al. book Causality: Rubin causal model Neyman-Rubin model

  6. Rubin’s potential outcome Counterfactual intervention sleep 7 hrs (vs 8 hrs) health e.g., what would have happen had the same person who sleeps 7 hrs slept 8 hrs instead?

  7. Rubin’s potential outcome Counterfactual intervention cigarette (vs pipe) health e.g., what would have happen had the same person who smokes pipe smoked cigarette instead?

  8. Rubin’s advice Define estimand before trying to estimate it from data. Counterfactual intervention: why counterfactual? we cannot jump into the same river twice fundamentally missing data problem define estimand in terms of complete data try to estimate it in the presence of missing data Experiment: randomized assignment or intervention Observational study: actual intervention not ethical

  9. Today’s reference is Judea Pearl, Causality What is a causal model and what it can do for us? How to learn a causal model, structure and parameters?

  10. Cochran example Soil fumigant Oat crop yields Eelworm population Last year -- unobserved Before treatment After treatment End of season Causal diagram Birds -- unobserved

  11. Soil fumigant Oat crop yields Eelworm population Farmers insist on they decide ,which depends on on ? How to define causal effect of Can it be obtained from passive observations?

  12. Causal Model Soil fumigant Oat crop yields Eelworm population Causal diagram: more than conditional independence

  13. Causal Model Causal diagram Structural equations ’s are independent

  14. Rubin’s potential outcome Counterfactual intervention

  15. Non-experimental observations Repeat 1 million times Get a new set of known black A million copies of return End

  16. Causal effect: intervention Repeat 1 million times Get a new set of black A distribution of End black

  17. Let’s play a game My code observing mode You guess My code intervening mode

  18. ?

  19. A million Not a million Causal effect may not be identifiable from observational study

  20. But can we express without

  21. = = = =

  22. You guess

  23. What is a causal model and what it can do for us? How to learn a causal model, structure and parameters?

More Related