Skip to main content
SpringerLink
Log in

Derivations of learning statistics from absorbing Markov chains

  • Published:
Psychometrika Aims and scope Submit manuscript

Abstract

Learning-process statistics for absorbing Markov-chain models are developed by using matrix methods exclusively. The paper extends earlier work by Bernbach by deriving the distribution of the total number of errors, u-tuples, autocorrelation of errors, sequential statistics, and the expectation and variance of all statistics presented. The technique is then extended to latency derivations including the latencies of sequential statistics. Suggestions are made for using the sequential-statistic algorithm in a maximum-likelihood estimation procedure. The technique is important because statistics for very large absorbing matrices can be easily computed without going through tedious theoretical calculations to find explicit mathematical expressions.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Atkinson, R. C., & Estes, W. K. In R. D. Luce, R. R. Bush, and E. Galanter (Eds.),Handbook of mathematical psychology. New York: Wiley, 1963, pp. 121–268.

    Google Scholar 

  • Bush, R. R. Sequential properties of linear models. In R. R. Bush and W. K. Estes (Eds.),Studies in mathematical learning theory. Stanford: Stanford Univ. Press, 1959, pp. 215–227.

    Google Scholar 

  • Bernbach, H. A. Derivation of learning process statistics for a general Markov model.Psychometrika, 1966,31, 225–234.

    Google Scholar 

  • Bower, G. H. Application of a model to paired-associate learning.Psychometrika, 1961,26, 255–280.

    Google Scholar 

  • Bower, G. H. & Trabasso, T. Concept-identification. In R. C. Atkinson (Ed.),Studies in mathematical psychology. Stanford: Stanford Univ. Press, 1964, pp. 32–94.

    Google Scholar 

  • Kemeny, J. G., & Snell, L. J.Finite Markov chains. Princeton: D. Van Nostrand, 1960.

    Google Scholar 

  • Millward, R. An all-or-none model for noncorrection routines with elimination of incorrect responses.Journal of Mathematical Psychology, 1964,1, 392–404.

    Google Scholar 

  • Millward, R. Latency in a modified paired-associate learning experiment.Journal of Verbal Learning and Verbal Behavior, 1964,3, 309–316.

    Google Scholar 

  • Nahinsky, I. D. Statistics-and-moment-parameter estimates for a duoprocess paired-associate learning model.Journal of Mathematical Psychology, 1967,4, 140–150.

    Google Scholar 

  • Restle, F. Learning paired associates. In R. C. Atkinson (Ed.),Studies in mathematical psychology. Stanford: Stanford Univ. Press, 1964, pp. 116–172.

    Google Scholar 

  • Suppes, P., Groen, G., & Schlag-Rey, M. A model for response latency in paired-associate learning.Journal of Mathematical Psychology, 1966,3, 99–128.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Brown University, USA

    Richard B. Millward

Authors
  1. Richard B. Millward
    View author publications

    You can also search for this author in PubMed Google Scholar

Additional information

The author is indebted to his students Thomas Wiekens and Richard Freund who were helpful in the development of this paper. Support was received for this work from Grant MH-11255 from the National Institutes of Mental Health.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Millward, R.B. Derivations of learning statistics from absorbing Markov chains. Psychometrika 34, 215–232 (1969). https://doi.org/10.1007/BF02289345

Download citation

  • Received:

  • Revised:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF02289345

Keywords

Search

Navigation