Learning as Hypothesis Testing: Learning Conditional and Probabilistic Information


Complex constraints like conditionals ('If A, then B') and probabilistic constraints ('The probability that A is p') pose problems for Bayesian theories of learning. Since these propositions do not express constraints on outcomes, agents cannot simply conditionalize on the new information. Furthermore, a natural extension of conditionalization, relative information minimization, leads to many counterintuitive predictions, evidenced by the sundowners problem and the Judy Benjamin problem. Building on the notion of a `paradigm shift' and empirical research in psychology and economics, I argue that the model of hypothesis testing can explain how people learn complex, theory-laden propositions like conditionals and probability constraints. Theories are formalized as probability distributions over a set of possible outcomes and theory change is triggered by a constraint which is incompatible with the initial theory. This leads agents to consult a higher order probability function, or a 'prior over priors,' to choose the most likely alternative theory which satisfies the constraint. The hypothesis testing model is applied to three examples: learning a simple probabilistic constraint involving coin bias, the sundowners problem for conditional learning, and the Judy Benjamin problem for learning conditional probability constraints.



External links

  • This entry has no external links. Add one.
Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

  • Only published works are available at libraries.

Similar books and articles

Strategic Learning and its Limits.H. Peyton Young - 2004 - Oxford University Press UK.
Influence of Conditionals on Belief Updating.Borut Trpin - 2018 - Dissertation, University of Ljubljana
Betting on conditionals.Jean Baratgin, David E. Over & Guy Politzer - 2010 - Thinking and Reasoning 16 (3):172-197.
A stimulus-trace hypothesis for statistical learning theory.Robert S. Witte - 1959 - Journal of Experimental Psychology 57 (5):273.
Probability and conditionals.Robert C. Stalnaker - 1970 - Philosophy of Science 37 (1):64-80.
Learning Conditional Information.Igor Douven - 2012 - Mind and Language 27 (3):239-263.


Added to PP

204 (#74,817)

6 months
36 (#58,844)

Historical graph of downloads
How can I increase my downloads?

Author's Profile

Jonathan Vandenburgh
Stanford University

Citations of this work

No citations found.

Add more citations

References found in this work

The Structure of Scientific Revolutions.Thomas S. Kuhn - 1962 - Chicago, IL: University of Chicago Press. Edited by Ian Hacking.
The Structure of Scientific Revolutions.Thomas Samuel Kuhn - 1962 - Chicago: University of Chicago Press. Edited by Otto Neurath.
The Logic of Decision.Richard C. Jeffrey - 1965 - New York, NY, USA: University of Chicago Press.
The origin of concepts.Susan Carey - 2009 - New York: Oxford University Press.
Causality.Judea Pearl - 2000 - New York: Cambridge University Press.

View all 18 references / Add more references