A Note On G-normal Distributions

2014/10/30 by Yongsheng Song, Song, Yongsheng
Mathematics · Decision Sciences · #Statistical Distribution Estimation and Applications #Fuzzy Systems and Optimization #Probability and Risk Models

paper · pdf · doi:10.48550/arxiv.1410.8225

Abstract

As is known, the convolution μ*ν of two G-normal distributions μ, ν with different intervals of variances may not be G-normal. We shows that μ*ν is a G-normal distribution if and only if (σ_μ)/(\underlineσ_μ)=(σ_ν)/(\underlineσ_ν).

Related

• A note on characterizations of G-normal distribution
• Comparing the G-Normal Distribution to its Classical Counterpart
• Stein Type Characterization for G-normal Distributions
• On Normal Variance-Mean Mixtures
• Semi-G-normal: a Hybrid between Normal and G-normal (Full Version)