Download presentation
Presentation is loading. Please wait.
Published byKory Goodwin Modified over 9 years ago
1
Judea Pearl Computer Science Department UCLA www.cs.ucla.edu/~judea ROBUSTNESS OF CAUSAL CLAIMS
2
ROBUSTNESS: MOTIVATION The effect of smoking on cancer is, in general, non-identifiable (from observational studies). Smoking x y Genetic Factors (unobserved) Cancer u In linear systems: y = x + is non-identifiable.
3
ROBUSTNESS: MOTIVATION Z – Instrumental variable; cov( z,u ) = 0 Smoking y Genetic Factors (unobserved) Cancer u x Z Price of Cigarettes is identifiable
4
ROBUSTNESS: MOTIVATION Problem with Instrumental Variables: The model may be wrong! Smoking Z Price of Cigarettes x y Genetic Factors (unobserved) Cancer u
5
Smoking ROBUSTNESS: MOTIVATION Z1Z1 Price of Cigarettes Solution: Invoke several instruments Surprise: 1 = 2 model is likely correct x y Genetic Factors (unobserved) Cancer u Peer Pressure Z2Z2
6
ROBUSTNESS: MOTIVATION Z1Z1 Price of Cigarettes x y Genetic Factors (unobserved) Cancer u Peer Pressure Z2Z2 Smoking Greater surprise: 1 = 2 = 3 ….= n = q Claim = q is highly likely to be correct Z3Z3 ZnZn Anti-smoking Legislation
7
ROBUSTNESS: MOTIVATION xy Genetic Factors (unobserved) Cancer u Smoking Symptoms do not act as instruments remains non-identifiable s Symptom Why? Taking a noisy measurement ( s ) of an observed variable ( y ) cannot add new information
8
ROBUSTNESS: MOTIVATION x Genetic Factors (unobserved) Cancer u Smoking Adding many symptoms does not help. remains non-identifiable y Symptom S1S1 S2S2 SnSn
9
ROBUSTNESS: MOTIVATION Find if can evoke an equality surprise 1 = 2 = … n associated with several independent estimands of x y Given a parameter in a general graph Formulate: Surprise, over-identification, independence Robustness: The degree to which is robust to violations of model assumptions
10
ROBUSTNESS: FORMULATION Bad attempt: Parameter is robust (over identifies) f 1, f 2 : Two distinct functions if:
11
ROBUSTNESS: FORMULATION exex eyey ezez xyz bc x = e x y = bx + e y z = cy + e z R yx = b R zx = bc R zy = c constraint: (b) (c) y → z irrelvant to derivation of b
12
RELEVANCE: FORMULATION Definition 8 Let A be an assumption embodied in model M, and p a parameter in M. A is said to be relevant to p if and only if there exists a set of assumptions S in M such that S and A sustain the identification of p but S alone does not sustain such identification. Theorem 2 An assumption A is relevant to p if and only if A is a member of a minimal set of assumptions sufficient for identifying p.
13
ROBUSTNESS: FORMULATION Definition 5 (Degree of over-identification) A parameter p (of model M ) is identified to degree k (read: k -identified) if there are k minimal sets of assumptions each yielding a distinct estimand of p.
14
ROBUSTNESS: FORMULATION xy b z c Minimal assumption sets for c. x y z c x y z c G3G3 G2G2 x y z c G1G1 Minimal assumption sets for b. x y b z
15
FROM MINIMAL ASSUMPTION SETS TO MAXIMAL EDGE SUPERGRAPHS FROM PARAMETERS TO CLAIMS Definition A claim C is identified to degree k in model M (graph G ), if there are k edge supergraphs of G that permit the identification of C, each yielding a distinct estimand. TE ( x,z ) = R zx TE ( x,z ) = R zx Rzy ·x x y z x y z e.g., Claim: (Total effect) TE (x,z) = q x y z
16
CONCLUSIONS 1.Formal definition to ROBUSTNESS of causal claims: “A claim is robust when it is insensitive to violations of some of the model assumptions” 2.Graphical criteria and algorithms for computing the degree of robustness of a given causal claim.
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.