Hi Rich,
RN:I am interested in learning of any studies using human subjects concerning
RN:reasoning under uncertainty and/or causal inference. In particular, I would
RN:like to know of any useful computer algorithm that is based on the results
For causal inference, look for stuff by Tenenbaum & Griffiths, Cheng,
Cheng & Glymour, Steyvers, Gopnik, Hashem & Cooper, Sloman & Lagnado, etc.
I don't know of a computer algorithm, unfortunately.
Here's a few citations, though notably lacking Gopnik who seems not to be
in my .bib file (?!). (Citations packed by date, not by volume. Some
publication of the contents may have occured during storage.)
-Charles
- ------
@Article{ steyvers03:_infer_causal_networ,
author = {Mark Steyvers and Josh B. Tenenbaum and Eric-Jan
Wagenmakers and Ben Blum},
title = {Inferring Causal Networks from Observations and
Interventions},
journal = {Cognitive Science},
year = 2003,
volume = {Submitted},
number = { },
pages = { }
}
@InProceedings{ lagnado02:_learn_causal_struc,
author = {David A. Lagnado and Steven Sloman},
title = {Learning Causal Structure},
booktitle = {Proceedings of the Twenty-Fourth Annual Conference
of the Cognitive Science Society},
year = 2002,
address = {Maryland},
organization = {Cognitive Science Society}
}
@Article{ tenenbaum01:_struc,
author = {Joshua B. Tenenbaum and Thomas L. Griffiths},
title = {Structure learning in human causal induction},
journal = {Advances in Neural Information Processing Systems},
year = {2001},
volume = 13,
annote = {PS version from author's website, January 2001. ``We
argue that a complete account of causal induction
should also consider how people learn the underlying
causal graph structure, and we propose to model this
inductive process as a Bayesian inference."}
}
@InProceedings{ hashem96:_hcd,
author = {Hashem, M.D., {Ahmad I.} and Cooper, {M.D., Ph.D.},
{Gregory F.}},
title = {Human Causal Discovery from Observational Data},
booktitle = {Proceedings of the 1996 symposium of the American
Medical Information Association},
pages = {27-31},
year = 1996,
organization = {American Medical Information Association},
abstract = "``Utilizing Bayesian belief networks as a model of
causality, we examined medical students' ability to
discover causal relatioships from observational
data. Nine sets of patient cases were generated from
relatively simple causal belief networks by
stochastic simulation. Twenty participants examined
the data sets and attempted to discover the
underlying causal relationships. Performance was
poor in general, except at discovering the absence
of a causal relationship. This work supports the
potential for combining human and computer methods
for causal discovery.''",
keywords = "causation; bayes nets; discovery; cognitive
psychology;",
annote = {The authors explore the probabilistic account of
causal inference. `Roughly, this account says that a
cause is that which alters one's probability of the
effect.' The paper seems to show that people are
very poor at using information from a third variable
to determine causal relations between two
others. The study should be redone using less
abstract data.}
}
@MastersThesis{ hashem96:_thesis,
author = {Ahmad I. Hashem},
title = {Human Causal Discovery from Observational Data: A
{B}ayesian Approach},
school = {University of Pittsburgh},
year = 1996,
address = {Faculty of Arts and Sciences},
month = {August},
annote = {Sent as msword file by Hashem Jan 31, 2001.}
}
@Article{ cheng:1997,
author = "Patricia W. Cheng",
title = "From Covariation to Causation: A Causal Power
Theory",
journal = "Psychological Review",
volume = "104",
number = "2",
pages = "367-405",
abstract = "``Because causal relations are neither observable
nor deducible, they must be induced from observable
events. The 2 dominant approaches to the psychology
of causal induction---the covariation approach and
the causal power approach---are each crippled by
fundamental problems. This article proposes an
integration of these approaches that overcomes these
problems. The proposal is that reasoners innately
treat the relation between covariation (a function
defined in terms of observable events) and causal
power (an unobservable entity) as that between
scientists' law or model and their theory explaining
the model. This solution is formalized in the power
PC theory, a causal power theory of the
probabilistic contrast model (P.W. Cheng \&
L.R. Novick, 1990). The article reviews diverse old
and new empirical tests discriminating this theory
from previous models, none of which is justified by
a theory. The results uniquely support the power PC
theory.''",
keywords = "causal power, causation, causal perception, causal
induction, covariation",
annote = "see cheng97.tex",
year = "1997"
}
@InCollection{ glymcheng:1999,
author = {Clark Glymour and Patricia Cheng},
title = {Causal mechanism and probability: a normative
approach},
booktitle = {Rational models of cognition},
publisher = {Oxford Univ. Press},
pages = {},
year = 1998,
editor = {M. Oaksford and N. Chater},
address = {Oxford},
annote = {Manuscript from Glymour}
}
@Book{ glymour01:_arrows,
author = {Clark Glymour},
title = {The Mind's Arrows: {B}ayes Nets and Graphical Causal
Models in Psychology},
publisher = {MIT Press},
year = 2001,
address = {MIT}
}
@Article{ glymour98,
author = {C. Glymour},
title = {Learning Causes: Psychological Explanations of
Causal Explanation},
journal = {Minds and Machines},
year = 1998,
volume = 8,
number = 1,
pages = {39--60},
annote = {I argue that psychologists interested in human
causal judgment should understand and adopt a
representation of causal mechanisms by directed
graphs that encode conditional independence
(screening off) relations. I illustrate the benefits
of that representation, now widely used in computer
science and increasingly in statistics, by (i)
showing that a dispute in psychology between
mechanist' and associationist' psychological
theories of causation rests on a false and confused
dichotomy; (ii) showing that a recent, much-cited
experiment, purporting to show that human subjects,
incorrectly let large causes overshadow' small
causes, misrepresents the most likely, and
warranted, causal explanation available to the
subjects, in the light of which their responses were
normative; (iii) showing how a recent psychological
theory (due to P. Cheng) of human judgment of causal
power can be considerably generalized: and (iv)
suggesting a range of possible experiments comparing
human and computer abilities to extract causal
information from associations.},
note = {Extensive handwritten notes on manuscript version}
}
- --
Charles R. Twardy www.csse.monash.edu.au/~ctwardy
Monash University sarbayes.org
Computer Sci. & Software Eng.
+61(3) 9905 5823 (w) 5146 (fax)
