Hostname: page-component-5f745c7db-96s6r Total loading time: 0 Render date: 2025-01-06T06:44:12.778Z Has data issue: true hasContentIssue false
  • English
  • Français

A Functional Equation Analysis of Two Learning Models

Published online by Cambridge University Press:  01 January 2025

Laveen Kanal
Laveen Kanal*
Affiliation:
General Dynamics/Electronics, Rochester, New York
Get access Rights & Permissions [Opens in a new window]

Abstract

One-absorbing barrier random walks arising from Luce's nonlinear beta model for learning and a linear commuting-operator model (called the alpha model) are considered. Functional equations for various statistics are derived from the branching processes defined by the two models. Solutions to general functional equations, satisfied by statistics of the alpha and beta models, are obtained. The methods presented have application to other learning models.

Type
Original Paper
Information
Psychometrika , Volume 27 , Issue 1 , March 1962 , pp. 89 - 104
Copyright
Copyright © 1962 The Psychometric Society

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Footnotes

*

Abstracted from portions of the author's doctoral dissertation, University of Pennsylvania, June 1960. The author is indebted to Robert R. Bush, his dissertation supervisor for the valuable help and encouragement received from him and to R. Duncan Luce for many helpful discussions and for partial support from an NSF grant.

†

Formerly at the Moore School of Electrical Engineering, University of Pennsylvania, Philadelphia, Pa. The author is grateful to J. G. Brainerd, S. Gorn, and C. N. Weygandt of the Moore School, and N. F. Finkelstein, D. Parkhill and A. A. Wolf of General Dynamics for their encouragement.

References

Adams, C. R. On the linear ordinaryq-difference equation. Ann. Math., 1929, 30, 195–205.CrossRefGoogle Scholar
Adams, C. R. Linearq-difference equations. Bull. Amer. math. Soc., 1931, 37, 361–400.CrossRefGoogle Scholar
Bellman, R. On a certain class of functional equations. In Harris, T. E., Bellman, R. and Shapiro, H. N. (Eds.), Functional equations occurring in decision processes, Santa Monica, Calif.: Rand Corp., 1952.Google Scholar
Bush, R. R. Some properties of Luce's beta model for learning. In Arrow, K. J., Karlin, S., and Suppes, P. (Eds.), Proceedings of the First Stanford Symposium on mathematical methods in the social sciences, Stanford, Calif.: Stanford Univ. Press, 1960.Google Scholar
Bush, R. R. and Estes, W. K. Studies in mathematical learning theory, Stanford, Calif.: Stanford Univ. Press, 1959.Google Scholar
Bush, R. R., Galanter, E. and Luce, R. D. Tests of the beta model. In Bush, R. R. and Estes, W. K. (Eds.), Studies in mathematical learning theory, Stanford, Calif.: Stanford Univ. Press, 1959.Google Scholar
Bush, R. R. and Mosteller, F. A comparison of eight models. In Bush, R. R. and Estes, W. K. (Eds.), Studies in mathematical learning theory, Stanford, Calif.: Stanford Univ. Press, 1959.Google Scholar
Bush, R. R. and Mosteller, F. Stochastic models for learning, New York: Wiley, 1955.CrossRefGoogle Scholar
Bush, R. R. and Sternberg, S. A single-operator model. In Bush, R. R. and Estes, W. K. (Eds.), Studies in mathematical learning theory, Stanford, Calif.: Stanford Univ. Press, 1959.Google Scholar
Fey, C. Investigation of some mathematical models for learning. J. exp. Psychol., 1961, 61, 455–461.CrossRefGoogle ScholarPubMed
Kanal, L. Analysis of some stochastic process arising from a learning model. Unpublished doctoral thesis, Univ. Penn., 1960.Google Scholar
Lamperti, J. and Suppes, P. Some asymptotic properties of Luce's beta learning model. Psychometrika, 1960, 25, 233–241.CrossRefGoogle Scholar
Luce, R. D. Individual choice behavior, New York: Wiley, 1959.Google Scholar
Tatsuoka, M. Asymptotic mean and variance of number of errors for the beta model. Unpublished memo. PC-11, 1958.Google Scholar
Tatsuoka, M. and Mosteller, F. A commuting-operator model. In Bush, R. R. and Estes, W. K. (Eds.), Studies in mathematical learning theories, Stanford, Calif.: Stanford Univ. Press, 1959.Google Scholar