Limit Theory for M-Estimates in an Integrated Infinite Variance
- 1 June 1991
- journal article
- research article
- Published by Cambridge University Press (CUP) in Econometric Theory
- Vol. 7 (2) , 200-212
- https://doi.org/10.1017/s0266466600004400
Abstract
We consider the limiting distributions of M-estimates of an “autoregressive” parameter when the observations come from an integrated linear process with infinite variance innovations. It is shown that M-estimates are, asymptotically, infinitely more efficient than the least-squares estimator (in the sense that they have a faster rate of convergence) and are conditionally asymptotically normal.Keywords
This publication has 10 references indexed in Scilit:
- Inference for Near-Integrated Time Series With Infinite VarianceJournal of the American Statistical Association, 1990
- Inference for Near-Integrated Time Series with Infinite VarianceJournal of the American Statistical Association, 1990
- Time Series Regression With a Unit Root and Infinite-Variance ErrorsEconometric Theory, 1990
- On the First-Order Autoregressive Process with Infinite VarianceEconometric Theory, 1989
- Limit theory for autoregressive‐parameter estimates in an infinite‐variance random walkThe Canadian Journal of Statistics / La Revue Canadienne de Statistique, 1989
- Some mixing properties of time series modelsStochastic Processes and their Applications, 1985
- Convergence of Stochastic ProcessesPublished by Springer Nature ,1984
- A new approach to decomposition of economic time series into permanent and transitory components with particular attention to measurement of the ‘business cycle’Journal of Monetary Economics, 1981
- A bivariate stable characterization and domains of attractionJournal of Multivariate Analysis, 1979
- Weak Convergence of MeasuresPublished by Society for Industrial & Applied Mathematics (SIAM) ,1971