Testing for mean reversion in heteroskedastic data II: Autoregression tests based on Gibbs-sampling-augmented randomization

Chang Jin Kim, Charles R. Nelson

Research output: Contribution to journalArticlepeer-review

22 Citations (Scopus)


A decade ago Fama and French [Fama, E.G., French, K.R., 1988. Permanent and temporary components of stock prices. J. Political Econ. 96 (2) 246-273] estimated that 40% of variation in stock returns was predictable over horizons of 3-5 yr, which they attributed to a mean reverting stationary component in prices. While it has been clear that the Depression and war years exert a strong influence on these estimates, it has not been clear whether the large returns of that period contribute to the information in the data or rather are a source of noise to be discounted in estimation. This paper uses the Gibbs-sampling-augmented randomization methodology to address the problem of heteroskedasticity in estimation of multi-period return autoregressions. Extending the sample period to 1995, we find little evidence of mean reversion. Examining subsamples, only 1926-1946 provides any evidence of mean reversion, while the post war period is characterized by mean aversion. A test of structural change suggests that this difference between pre and post war periods is significant.

Original languageEnglish
Pages (from-to)385-396
Number of pages12
JournalJournal of Empirical Finance
Issue number4
Publication statusPublished - 1998 Oct

Bibliographical note

Funding Information:
Kim greatly appreciates support from the department. Nelson acknowledges support from the Van Voorhis endowment at the University of Washington and from the National Science Foundation.

Copyright 2018 Elsevier B.V., All rights reserved.


  • Autoregression tests
  • C15
  • C22
  • G12
  • Gibbs sampling
  • Mean aversion
  • Mean reversion
  • Randomization

ASJC Scopus subject areas

  • Finance
  • Economics and Econometrics


Dive into the research topics of 'Testing for mean reversion in heteroskedastic data II: Autoregression tests based on Gibbs-sampling-augmented randomization'. Together they form a unique fingerprint.

Cite this