Authors | |
Abstract |
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.
|
Keywords | Hypothesis Testing Bayesian Learning Conditionals Probability |
Categories | (categorize this paper) |
Options |
![]() ![]() ![]() ![]() |
Download options
References found in this work BETA
The Structure of Scientific Revolutions.Thomas Samuel Kuhn - 1962 - Chicago: University of Chicago Press.
View all 18 references / Add more references
Citations of this work BETA
No citations found.
Similar books and articles
Why is Bayesian Confirmation Theory Rarely Practiced?Robert W. P. Luk - 2019 - Science and Philosophy 7 (1):3-20.
Influence of Conditionals on Belief Updating.Borut Trpin - 2018 - Dissertation, University of Ljubljana
Seeking Confirmation Is Rational for Deterministic Hypotheses.Joseph L. Austerweil & Thomas L. Griffiths - 2011 - Cognitive Science 35 (3):499-526.
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.
Learning Conditional Information by Jeffrey Imaging on Stalnaker Conditionals.Mario Günther - 2018 - Journal of Philosophical Logic 47 (5):851-876.
Popper's Severity of Test as an Intuitive Probabilistic Model of Hypothesis Testing.Fenna H. Poletiek - 2009 - Behavioral and Brain Sciences 32 (1):99-100.
Awareness and Hypothesis Testing in Concept and Operant Learning.Dianne S. Silver, Eli Saltz & Vito Modigliani - 1970 - Journal of Experimental Psychology 84 (2):198.
A Test of a General Utility Theory Model for Probability Learning.Kenneth B. Little, Yvonne Brackbill & Stephen H. Kassel - 1962 - Journal of Experimental Psychology 63 (4):404.
The Conditional Construal of Conditional Probability.Alan Roy Hajek - 1993 - Dissertation, Princeton University
Analytics
Added to PP index
2020-11-10
Total views
137 ( #85,372 of 2,507,886 )
Recent downloads (6 months)
25 ( #34,917 of 2,507,886 )
2020-11-10
Total views
137 ( #85,372 of 2,507,886 )
Recent downloads (6 months)
25 ( #34,917 of 2,507,886 )
How can I increase my downloads?
Downloads