Hostname: page-component-6bf8c574d5-h6jzd Total loading time: 0.001 Render date: 2025-02-22T04:04:02.163Z Has data issue: false hasContentIssue false
  • English
  • Français

Precriterion Stationarity in Markovian Learning Models

Published online by Cambridge University Press:  01 January 2025

Henry M. Halff
Henry M. Halff*
Affiliation:
University of Illinois at Urbana-Champaign
*
Requests for reprints should be sent to Henry M. Halff, Department of Psychology, University of Illinois, Champaign, Illinois 61820.
Get access Rights & Permissions [Opens in a new window]

Abstract

Two forms of stationarity prior to criterion in absorbing Markov chains are examined. Both forms require that the probability of a particular response on a particular trial before absorption be independent of trial number. The stronger of these forms holds that this is true independent of starting state; the weaker, only for a specified set of starting probabilities. Simple, necessary and sufficient conditions for both forms are developed and applied to several examples.

Keywords

performancematrixall-or-none learning
Type
Original Paper
Information
Psychometrika , Volume 41 , Issue 3 , September 1976 , pp. 301 - 320
Copyright
Copyright © 1976 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

The author would like to thank Charles Lewis for his help in developing this article, and Peter Polson of the University of Colorado and an anonymous referee for several fruitful suggestions made in reviews of earlier versions.

References

Reference Note

Halff, H. M. Appendix to “Precriterion stationary in Markovian learning models.” Unpublished manuscript, 1976. (Available from Henry M. Halff, Department of Psychology, University of Illinois, Champaign, Illinois 61820).CrossRefGoogle Scholar

References

Bower, G. H. Application of a model to paired-associates learning. Psychometrika, 1961, 26, 225–280.CrossRefGoogle Scholar
Bower, G. H., & Trabasso, T. R. Concept identification. In Atkinson, R. C.(Eds.), Studies in mathematical psychology, 1964, Stanford, California: Stanford University Press.Google Scholar
Bush, R. R., & Mosteller, F. A mathematical model for simple learning. Psychological Review, 1951, 58, 313–323.CrossRefGoogle ScholarPubMed
Greeno, J. G. Paired associates learning with short-term retention: Mathematical analysis and data regarding identification. Journal of Mathematical Psychology, 1967, 3, 388–411.CrossRefGoogle Scholar
Greeno, J. G. Identifiability and statistical properties of two-stage learning with no successes in the initial stage. Psychometrika, 1968, 33, 173–215.CrossRefGoogle ScholarPubMed
Greeno, J. G., Millward, R. B., & Merryman, C. T. Matrix analysis of identifiability of some finite Markov models. Psychometrika, 1971, 36, 389–408.CrossRefGoogle Scholar
Greeno, J. G., & Steiner, T. E. Markovian processes with identifiable states: General considerations and an application to all-or-none learning. Psychometrika, 1964, 29, 309–333.CrossRefGoogle Scholar
Greeno, J. G., & Steiner, T. E. Comments on “Markovian processes with identifiable states: General considerations and an application to all-or-none learning.”. Psychometrika, 1968, 33, 169–172.CrossRefGoogle Scholar
Millward, R. B. Derviation of learning statistics from absorbing Markov chains. Psychometrika, 1969, 34, 215–231.CrossRefGoogle Scholar
Polson, P. G. Statistical methods for a general theory of all-or-none learning. Psychometrika, 1970, 35, 51–72.CrossRefGoogle Scholar
Polson, P. G., & Greeno, J. G. Nonstationary performance before all-or-none learning. Psychological Review, 1969, 76, 227–231.CrossRefGoogle Scholar
Restle, F. The selection of strategies in cue learning. Psychological Review, 1962, 69, 329–343.CrossRefGoogle ScholarPubMed
Restle, F. The significance of all-or-none learning. Psychological Bulletin, 1965, 62, 313–324.CrossRefGoogle Scholar
Steiner, T. E., & Greeno, J. G. An analysis of some conditions for representing N state Markov processes as general all or none models. Psychometrika, 1969, 34, 461–487.CrossRefGoogle Scholar
Suppes, P., & Ginsberg, R. A fundamental property of all-or-none models, binomial distribution of reponses prior to conditioning, with application to concept formation in children. Psychological Review, 1963, 70, 139–162.CrossRefGoogle Scholar
Wandell, B. A., Greeno, J. G., & Egan, D. E. Equivalence classes of functions of finite Markov chains. Journal of Mathematical Psychology, 1975, 11, 391–403.CrossRefGoogle Scholar