Autoregressive models with short-tailed symmetric distributions

Abstract

Symmetric short-tailed distributions do indeed occur in practice but have not received much attention particularly in the context of autoregression. We consider a family of such distributions and derive the modified maximum likelihood estimators of the parameters. We show that the estimators are efficient and robust. We develop hypothesis-testing procedures.

Keywords:

• short-tailedness
• inliers
• autoregression
• nonlinear model
• modified likelihood
• hypothesis testing

Acknowledgements

We are very grateful to the referee for many helpful comments.