5. Causal assessment
‘What Causes What’
Different things we may want to establish:
what’s the cause of a patient’s illness
who is (legally / morally) responsible for some state of affairs
what are the causes of unemployment
what causes marriage dissolution or migration behaviour
what causes dysfunction in an organisation
which pathways explain some cellular behaviour
…
5
6. Goals of causal analysis
Knowledge-oriented
Understand and explain a
phenomenon of interest
Action-oriented
Predict, intervene on, control a
phenomenon of interest
Design / model / debug a
system / environment
6
7. Do causes need to be causes?
Consider:
Smoking and cancer are associated. Should I quit smoking?
Smoking causes cancer. Should I quit smoking?
Causes trigger actions. Mere beliefs can’t, nor mere associations.
7Source: http://xkcd.com/552/
8. Scientific practice first
CitS / PSP / PI
Philosophical questions about causation (and other
topics) are motivated by methodological and
practical problems in real science
Start from scientific practice to bottom up
philosophy
Partly descriptive and partly normative
No conceptual ‘straightjacket’
8
9. 5 philosophical questions
Metaphysics
What is causality? What kind of things
are causes and effects?
Semantics
What does it mean that C causes E?
Epistemology
What notions guide causal reasoning?
How can we use C to explain E?
Methodology
How to establish whether C causes E?
Or how much of C causes E?
Use
What to do once we know that C
causes E?
5 scientific problems
Inference
Does C cause E? To what extent?
Prediction
What to expect if C does (not) cause
E?
Explanation
How does C cause or prevent E?
Control
What factors to hold fixed to study the
relation between C and E?
Reasoning
What considerations enter in
establishing whether / how / to what
extent C causes E?
9
11. How many concepts? Many!
Causality
Polysemic, thick concept
Causal verbs
Pulling, pushing, binding, …
Causal methods
Tracking what varies with what
Understanding what produces what, and how, and when
Different sources of evidence
Evidence of difference making, of production
…
11
16. ‘Statistical’ causes
Gather a large number of observations,
organise them in variables
E.g. socio-biological characteristics (exposure) and cancer
rates (disease)
Study the (in)dependencies between variables,
robustness and stability of correlations
Establish stable patterns of (in)dependencies
to identify risk factors and possible interventions
16
17. What does a causal model do?
A causal model:
models the properties of a (social) system
detects (causal) relations between the properties of
the system
explains the functioning of the system through its
causes
17
19. Structural equations and explanation
Y=X+
X, Y : explanatory and response variables
Xs explain Y
Xs are relevant causal factors in the causal
mechanism
19
21. Causal discovery is reasoning about variations.
To establish causes we need difference.
21
22. ‘Statistical’ variations
“Gather data about socio-economic status, occupation,
diet, smoking behaviour and see how steadily they
are associated with cancer”
Study how variations in exposure are related to
variations in disease
How different levels of exposure change the probability
of disease
Statistical reasoning: search for those factors explaining
the variance of the outcome
22
24. Variations in MillAgreement:
comparing different instances in which the
phenomenon occurs.
Difference:
comparing instances in which the
phenomenon does occur with similar
instances in which it does not.
Residues:
subducting from any given phenomenon all
the portions which can be assigned to
known causes, the remainder will be the
effect of the antecedents which had been
overlooked or of which the effect was as
yet an un-known quantity.
Concomitant Variation:
in presence of permanent causes or
indestructible natural agents that are
impossible either to exclude or to isolate,
we can neither hinder them from being
present nor contrive that they shall be
present alone. Comparison between
concomitant variations will enable us to
detect the causes.
Mill (1843), System of Logic
The experimental method is based
on the Baconian rule of varying
the circumstances
The Four Methods are all based on
the evaluation of variations
24
25. Variations in Durkheim
Durkheim (1897), Le suicide
A study into the variability of suicide rate
A search for the causes making suicide rate vary
Durkheim (1885), Les règles de la méthode sociologique
The method of concomitant variations
makes sociology scientific
25
26. Learning ‘ordinary’ causes
Humean regularity
Instances of smoke follow instances of fire
Can’t establish logical, necessary link
Create expectation, project causal belief onto the future
Epistemology of causal modelling seems to be at
variance with the Humean account
See next
26
27. Learning ‘scientific’ causes
Causal discovery (experiments, statistics)
Search for differences
Explaining differences
Variation, difference, comes first
27
28. Regularity too
Statistical regularity
Causal methodology needs regularity as a constraint on
variations, differences
Scientific causes are ‘generic’
Population-level, repeatable
Hence we need regularity to establish generic level
28
30. Inference, Prediction,
Explanation, Control,
Reasoning
Causal Mosaic
Metaphysics, Semantics,
Epistemology,
Methodology, Use
Necessary
and
sufficient Levels
Evidence
Probabilis
tic
causality
Counterfa
ctuals
Manipulat
ion
Invariance
Exogeneit
y
Simpson’s
Paradox
ProcessMechanism
Informati
on
Dispositio
ns
Regularity
Variation
Action
Inference
Validity
Truth
30
31. Philosophical theory meets scientific practice
Scientific practice first
Then, be precise about your question, target specific
scientific challenges
Causal pluralism, in the form of ‘causal mosaic’, is a
sophisticated philosophical view
Methodology of causality is rich and diverse
Choose the method best adapted to your problem
Epistemology of causality is about how we find out about
causes
Variation guides causal reasoning in various forms
31