Weighted Least Absolute Deviations Estimation for Arma Models with Infinite Variance

  title={Weighted Least Absolute Deviations Estimation for Arma Models with Infinite Variance},
  author={Jiazhu Pan and Hui Wang and Qiwei Yao},
For autoregressive and moving-average (ARMA) models with infinite variance innovations, quasi-likelihood based estimators (such as Whittle’s estimators ) suffer from complex asymptotic distributions depending on unknown tail indices. This makes the statistical inference for such models difficult. In contrast, the least absolute deviations estimators (LADE) are more appealing in dealing with heavy tailed processes. In this paper, we propose a weighted least absolute deviations estimator (WLADE… CONTINUE READING


Publications referenced by this paper.
Showing 1-10 of 15 references

A User’s Guide to Heavy Tails

  • R. J. Adler, R. Feldaman, M. Taqqu
  • 1997
Highly Influential
7 Excerpts

Parameter estimation for ARMA models with

  • T. Mikosch, T. Gadrich, R. J. Adler
  • 1995
Highly Influential
3 Excerpts

Limit theory for moving averagers of random variables with regularly varying tail probabilities

  • R. A. Davis
  • Annals of Probability
  • 1985
Highly Influential
10 Excerpts

Self-weighted LAD estimation for infinite variance autoregressive models

  • S. Ling
  • Journal of the Royal Statistical Society B 67,
  • 2005
2 Excerpts

Lp-estimators in ARCH models

  • L. Horvath, F. Liese
  • Journal of Statistical Planning and Inference
  • 2004
1 Excerpt

M-estimation for autoregressions with infinite variance

  • R. A. Davis, K. Knight, J. Liu
  • Stochastic Processes and Their Applications
  • 1992
1 Excerpt

Density estimation for statistics and data analysis

  • W. Rudin
  • 1991
1 Excerpt

On the frequency of large stock returns: putting booms and busts into perspective

  • D. Jansen, C. De Vries
  • Review of Economics and Statistics
  • 1991

Similar Papers

Loading similar papers…