## Access

You are not currently logged in.

Access your personal account or get JSTOR access through your library or other institution:

## If You Use a Screen Reader

This content is available through Read Online (Free) program, which relies on page scans. Since scans are not currently available to screen readers, please contact JSTOR User Support for access. We'll provide a PDF copy for your screen reader.

# Bayesian Representation of Stochastic Processes Under Learning: De Finetti Revisited

Matthew O. Jackson, Ehud Kalai and Rann Smorodinsky
Econometrica
Vol. 67, No. 4 (Jul., 1999), pp. 875-893
Stable URL: http://www.jstor.org/stable/2999460
Page Count: 19
Since scans are not currently available to screen readers, please contact JSTOR User Support for access. We'll provide a PDF copy for your screen reader.
Preview not available

## Abstract

A probability distribution governing the evolution of a stochastic process has infinitely many Bayesian representations of the form $\mu =\int_{\Theta}\mu _{\theta }d\lambda (\theta)$. Among these, a natural representation is one whose components $(\mu _{\theta}\text{'}{\rm s})$ are "learnable" (one can approximate μ θ by conditioning μ on observation of the process) and "sufficient for prediction" ($\mu _{\theta}\text{'}{\rm s}$ predictions are not aided by conditioning on observation of the process). We show the existence and uniqueness of such a representation under a suitable asymptotic mixing condition on the process. This representation can be obtained by conditioning on the tail-field of the process, and any learnable representation that is sufficient for prediction is asymptotically like the tail-field representation. This result is related to the celebrated de Finetti theorem, but with exchangeability weakened to an asymptotic mixing condition, and with his conclusion of a decomposition into i.i.d. component distributions weakened to components that are learnable and sufficient for prediction.

• 875
• 876
• 877
• 878
• 879
• 880
• 881
• 882
• 883
• 884
• 885
• 886
• 887
• 888
• 889
• 890
• 891
• 892
• 893