Electronic Journal of Statistics

The empty set and zero likelihood problems in maximum empirical likelihood estimation

Wicher Bergsma, Marcel Croon, and L. Andries van der Ark

Full-text: Open access

Abstract

We describe a previously unnoted problem which, if it occurs, causes the empirical likelihood method to break down. It is related to the empty set problem, recently described in detail by Grendár and Judge (2009), which is the problem that the empirical likelihood model is empty, so that maximum empirical likelihood estimates do not exist. An example is the model that the mean is zero, while all observations are positive. A related problem, which appears to have gone unnoted so far, is what we call the zero likelihood problem. This occurs when the empirical likelihood model is nonempty but all its elements have zero empirical likelihood. Hence, also in this case inference regarding the model under investigation breaks down. An example is the model that the covariance is zero, and the sample consists of monotonically associated observations. In this paper, we define the problem generally and give examples. Although the problem can occur in many situations, we found it to be especially prevalent in marginal modeling of categorical data, when the problem often occurs with probability close to one for large, sparse contingency tables.

Article information

Source
Electron. J. Statist., Volume 6 (2012), 2356-2361.

Dates
First available in Project Euclid: 14 December 2012

Permanent link to this document
https://projecteuclid.org/euclid.ejs/1355495989

Digital Object Identifier
doi:10.1214/12-EJS750

Mathematical Reviews number (MathSciNet)
MR3020267

Zentralblatt MATH identifier
1295.62027

Subjects
Primary: 62G05: Estimation 62G10: Hypothesis testing
Secondary: 62H12: Estimation 62H15: Hypothesis testing 62H17: Contingency tables

Keywords
Empirical likelihood empty set problem zero likelihood problem marginal model optimization with constraints

Citation

Bergsma, Wicher; Croon, Marcel; van der Ark, L. Andries. The empty set and zero likelihood problems in maximum empirical likelihood estimation. Electron. J. Statist. 6 (2012), 2356--2361. doi:10.1214/12-EJS750. https://projecteuclid.org/euclid.ejs/1355495989


Export citation

References

  • Bergsma, W. P. (1997)., Marginal Models for Categorical Data. Tilburg University Press, Tilburg.
  • Bergsma, W. P., Croon, M. A., and Hagenaars, J. A. P. (2009)., Marginal models for dependent, clustered and longitudinal categorical data. Springer, New York.
  • Bergsma, W. P. and Rapcsák, T. (2005). An exact penalty method for smooth equality constrained optimization with application to maximum likelihood estimation., Eurandom technical report, 2005-001:1–21. http://www.eurandom.tue.nl/reports/2005/001-report.pdf
  • Chen, J., Variyath, A. M., and Abraham, B. (2008). Adjusted empirical likelihood and its properties., Journal of Computational and Graphical Statistics, 17(2):426–443.
  • Grendár, M. and Judge, G. (2009). Empty set problem of maximum empirical likelihood methods., Electronic Journal of Statistics, 3:1542–1555.
  • Liu, Y. and Chen, J. (2010). Adjusted empirical likelihood with high-order precision., The Annals of Statistics, 38(3):1341–1362.
  • Owen, A. B. (2001)., Empirical likelihood, volume 92. CRC press, New York.
  • Qin, J. and Lawless, J. (1994). Empirical likelihood and general estimating equations., The Annals of Statistics, pages 300–325.