The eschewed sinh-arcsinh t distribution

C. Jones, A. Pewsey

We revisit the sinh-arcsinh t (SAS-t) distribution introduced and studied in Rosco et al. (2011), primarily because the formulation of that model admits densities that can be bimodal. In this talk we reconsider a version of the model referred to in Rosco et al. (2011) that, because of it being renounced there, we refer to as the eschewed sinh-arcsinh t (ESAS-t) distribution. The ESAS-t model proves to be somewhat simpler than the SAS-t one and, on balance, given the pros and cons that we will identify in the talk, we now recommend the ESAS-t distribution over the SAS-t distribution as the preferable version of a sinh-arcsinh t distribution.

Keywords: Kurtosis, Skew t distribution, Skewness, Unimodality

Statistical Models
September 4, 2026  9:00 AM
Aula 24

V. Cueva López, M. J. Olmo Jiménez, J. Rodríguez Avi

S. Fernández Alonso, S. Díaz Vázquez, S. Montes Rodriguez

M. Pereda Vivo, C. Paroissin

S. Suarez-Fernandez, A. Bouchet, M. R. Oliveira, S. Montes, S. Diaz-Vazquez