russo silf07 explaining causal modelling
TRANSCRIPT
![Page 1: Russo Silf07 Explaining Causal Modelling](https://reader035.vdocument.in/reader035/viewer/2022070603/554f4eb0b4c905524c8b4cb3/html5/thumbnails/1.jpg)
Explaining causal modellingOR
What a causal model ought to explain
Federica RussoUniversité catholique de
Louvain
![Page 2: Russo Silf07 Explaining Causal Modelling](https://reader035.vdocument.in/reader035/viewer/2022070603/554f4eb0b4c905524c8b4cb3/html5/thumbnails/2.jpg)
2
Overview What is a causal model
Explanatory vocabulary in causal modelling
Modelling causal mechanisms
Causal-model explanations
Causal modelling vs. other models
![Page 3: Russo Silf07 Explaining Causal Modelling](https://reader035.vdocument.in/reader035/viewer/2022070603/554f4eb0b4c905524c8b4cb3/html5/thumbnails/3.jpg)
What is a causal model
![Page 4: Russo Silf07 Explaining Causal Modelling](https://reader035.vdocument.in/reader035/viewer/2022070603/554f4eb0b4c905524c8b4cb3/html5/thumbnails/4.jpg)
4
54
4
13
34
12
2
X1Economic
development
X2Social
development
X3Sanitary
infrastructures
X4Use of
sanitary infrastructure
sX5
Age structure
YMortality
45543344
31133
21122
14422
XXXXXXX
XXY
![Page 5: Russo Silf07 Explaining Causal Modelling](https://reader035.vdocument.in/reader035/viewer/2022070603/554f4eb0b4c905524c8b4cb3/html5/thumbnails/5.jpg)
5
Causal models
Rest on a number of assumptions
Model causal relations statisticallystatistically
Uncover stable variational relations
![Page 6: Russo Silf07 Explaining Causal Modelling](https://reader035.vdocument.in/reader035/viewer/2022070603/554f4eb0b4c905524c8b4cb3/html5/thumbnails/6.jpg)
Explanatory vocabulary in causal modelling
![Page 7: Russo Silf07 Explaining Causal Modelling](https://reader035.vdocument.in/reader035/viewer/2022070603/554f4eb0b4c905524c8b4cb3/html5/thumbnails/7.jpg)
7
Explanation in structural equations
Y=X+X, Y : explanatory and response variables
Xs explain Y
Intuitively:Xs explain Y
Xs account for Y
Xs are relevant causal factors in the causal mechanism
![Page 8: Russo Silf07 Explaining Causal Modelling](https://reader035.vdocument.in/reader035/viewer/2022070603/554f4eb0b4c905524c8b4cb3/html5/thumbnails/8.jpg)
8
CM explains variability in YY=X+
Variations in X explain variations in Y
How is explanation ‘quantified’?
r2 represents the fraction of variability in Y explained by X
r2 indicates how much variability in Y is accounted for by the regression function
![Page 9: Russo Silf07 Explaining Causal Modelling](https://reader035.vdocument.in/reader035/viewer/2022070603/554f4eb0b4c905524c8b4cb3/html5/thumbnails/9.jpg)
9
But … r2 measures the goodness of fit,
not the validity of the model
r2 doesn’t give any theoretical reason for the accounted variability
r2 depends on the correctness of assumptions
![Page 10: Russo Silf07 Explaining Causal Modelling](https://reader035.vdocument.in/reader035/viewer/2022070603/554f4eb0b4c905524c8b4cb3/html5/thumbnails/10.jpg)
10
The philosophical answer
Explanatory import is given by:
Covariate sufficiency
No-confounding
Background knowledge
![Page 11: Russo Silf07 Explaining Causal Modelling](https://reader035.vdocument.in/reader035/viewer/2022070603/554f4eb0b4c905524c8b4cb3/html5/thumbnails/11.jpg)
Modelling causal mechanisms
![Page 12: Russo Silf07 Explaining Causal Modelling](https://reader035.vdocument.in/reader035/viewer/2022070603/554f4eb0b4c905524c8b4cb3/html5/thumbnails/12.jpg)
12
Causal models model mechanisms
Most widespread conception:Mechanisms are made of physical processes, interactions, …, assembled to behave like a gear
But:What if we have
socio-economic-demographic variables?social and biological variables?
![Page 13: Russo Silf07 Explaining Causal Modelling](https://reader035.vdocument.in/reader035/viewer/2022070603/554f4eb0b4c905524c8b4cb3/html5/thumbnails/13.jpg)
13
A mixed mechanism
TreatmentPrevention
Socioeconomicdeterminants
Maternalfactors
Environmental contamination
Nutrientdeficiency
Injury
Healthy Sick
Personal illness control
Growthfaltering
Mortality
![Page 14: Russo Silf07 Explaining Causal Modelling](https://reader035.vdocument.in/reader035/viewer/2022070603/554f4eb0b4c905524c8b4cb3/html5/thumbnails/14.jpg)
14
The causal model incorporates social and biological variables
Modelling the mechanism gives the causal model explanatory power
![Page 15: Russo Silf07 Explaining Causal Modelling](https://reader035.vdocument.in/reader035/viewer/2022070603/554f4eb0b4c905524c8b4cb3/html5/thumbnails/15.jpg)
Causal-models explanations
![Page 16: Russo Silf07 Explaining Causal Modelling](https://reader035.vdocument.in/reader035/viewer/2022070603/554f4eb0b4c905524c8b4cb3/html5/thumbnails/16.jpg)
16
Causal modelling is a model of explanation
The formal structure of explanation is given
by the methodology of causal modelling:
Formulate the causal hypothesis
Build the statistical model
Draw consequences to conclude to empirical validity/invalidity of the hypothesis
![Page 17: Russo Silf07 Explaining Causal Modelling](https://reader035.vdocument.in/reader035/viewer/2022070603/554f4eb0b4c905524c8b4cb3/html5/thumbnails/17.jpg)
17
CM explanations are flexible:
they allow a va et viens between established theories and establishing theories
they participate in establishing new theories
negative results may trigger further research
![Page 18: Russo Silf07 Explaining Causal Modelling](https://reader035.vdocument.in/reader035/viewer/2022070603/554f4eb0b4c905524c8b4cb3/html5/thumbnails/18.jpg)
18
CM explanations allow control:
1) statisticalr2 measures amount of variability explained
2) epistemicCM requires coherence of resultswith background knowledge
3) metaphysicalCM requires ontological homogeneitybetween variables in the mechanism
![Page 19: Russo Silf07 Explaining Causal Modelling](https://reader035.vdocument.in/reader035/viewer/2022070603/554f4eb0b4c905524c8b4cb3/html5/thumbnails/19.jpg)
Causal modellingvs
other models of explanation
![Page 20: Russo Silf07 Explaining Causal Modelling](https://reader035.vdocument.in/reader035/viewer/2022070603/554f4eb0b4c905524c8b4cb3/html5/thumbnails/20.jpg)
20
CM vs deductive-nomological model well known problems with laws not all explanations involve deduction
CM vs statistical-relevance model S-R is too narrow in scope
CM vs causal-mechanical model it cannot account for mixed mechanisms
![Page 21: Russo Silf07 Explaining Causal Modelling](https://reader035.vdocument.in/reader035/viewer/2022070603/554f4eb0b4c905524c8b4cb3/html5/thumbnails/21.jpg)
21
CM vs manipulationist modelWoodward (2003)
A theory of causal explanation
Causal generalisations are change-relating
Change-relating relations are explanatory:they are invariant under a large class of interventions or environmental changes
![Page 22: Russo Silf07 Explaining Causal Modelling](https://reader035.vdocument.in/reader035/viewer/2022070603/554f4eb0b4c905524c8b4cb3/html5/thumbnails/22.jpg)
22
Generalisations show:(i) that the explanandum was to be expected(ii) how the explanandum would change
if initial conditions had changed
What-if-things-had-been-different questions
Relevant counterfactuals describe outcomes of interventions
Explanatory power is tested by means of counterfactual questions
![Page 23: Russo Silf07 Explaining Causal Modelling](https://reader035.vdocument.in/reader035/viewer/2022070603/554f4eb0b4c905524c8b4cb3/html5/thumbnails/23.jpg)
23
However …The manipulationist account:
Overlooks the role of background knowledge
Neglects the causal role of non-manipulable factors
Takes for granted what the causes are
![Page 24: Russo Silf07 Explaining Causal Modelling](https://reader035.vdocument.in/reader035/viewer/2022070603/554f4eb0b4c905524c8b4cb3/html5/thumbnails/24.jpg)
24
To sum upCausal modelling
Aims at explaining social phenomena
Makes essential use of explanatory vocabulary
Has explanatory power insofar as it models mechanism
![Page 25: Russo Silf07 Explaining Causal Modelling](https://reader035.vdocument.in/reader035/viewer/2022070603/554f4eb0b4c905524c8b4cb3/html5/thumbnails/25.jpg)
25
To concludeCausal modelling is a model of explanation
Among its virtues, over and above alternative models:
FlexibilityControl