Truncated-exponential skew-symmetric distributions

Abstract

The family of skew distributions introduced by Azzalini and extended by others has received widespread attention. However, it suffers from complicated inference procedures. In this paper, a new family of skew distributions that overcomes the difficulties is introduced. This new family belongs to the exponential family. Many properties of this family are studied, inference procedures developed and simulation studies performed to assess the procedures. Some particular cases of this family, evidence of its flexibility and a real data application are presented. At least 10 advantages of the new family over Azzalini's distributions are established.

Keywords:

• Azzalini skew distributions
• estimation
• exponential family
• skewness

Acknowledgements

The authors would like to thank the editor, the associate editor and the referee for careful reading and for their comments which greatly improved the paper.