Log-symmetric distributions: Statistical properties and parameter estimation

In this paper, we study the main statistical properties of the class of log-symmetric distributions, which includes as special cases bimodal distributions as well as distributions that have heavier/lighter tails than those of the log-normal distribution. This family includes distributions such as the log-normal, log-Student-t , harmonic law, Birnbaum–Saunders, Birnbaum– Saunders-t and generalized Birnbaum–Saunders. We derive quantile-based measures of location, dispersion, skewness, relative dispersion and kurtosis for the log-symmetric class that are appropriate in the context of asymmetric and heavy-tailed distributions. Additionally, we discuss parameter estimation based on both classical and Bayesian approaches. The usefulness of the logsymmetric class is illustrated through a statistical analysis of a real dataset, in which the performance of the log-symmetric class is compared with that of some competitive and very flexible distributions.

[1]  Samuel Kotz,et al.  Log-Skew-Normal and Log-Skew-t Distributions as Models for Family Income Data , 2002, Journal of Income Distribution®.

[2]  James R. Rieck,et al.  A log-linear model for the Birnbaum-Saunders distribution , 1991 .

[3]  O. Barndorff-Nielsen.  Exponentially decreasing distributions for the logarithm of particle size , 1977, Proceedings of the Royal Society of London. A. Mathematical and Physical Sciences.

[4]  Narayanaswamy Balakrishnan,et al.  Estimation in the Birnbaum-Saunders distribution based on scale-mixture of normals and the EM-algorithm , 2009 .

[5]  H. Akaike,et al.  Information Theory and an Extension of the Maximum Likelihood Principle , 1973 .

[6]  B. Dhillon.  Life Distributions , 1981, IEEE Transactions on Reliability.

[7]  G. C. Tiao,et al.  Bayesian inference in statistical analysis , 1973 .

[8]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[9]  Víctor Leiva,et al.  A new class of survival regression models with heavy-tailed errors: robustness and diagnostics , 2008, Lifetime data analysis.

[10]  A note on the harmonic law : A two-parameter family of distributions for ratios , 2008 .

[11]  W. Rogers,et al.  Understanding some long-tailed symmetrical distributions , 1972 .

[12]  James R. Rieck,et al.  A moment-generating function with application to the birnbaum-saunders distribution , 1999 .

[13]  José A. Díaz-García,et al.  A new family of life distributions based on the elliptically contoured distributions , 2005 .

[14]  Peter M. Bentler,et al.  Statistical Inference Based on Pseudo-Maximum Likelihood Estimators in Elliptical Populations , 1993 .

[15]  Z. Birnbaum,et al.  A new family of life distributions , 1969 .

[16]  E. Stacy.  A Generalization of the Gamma Distribution , 1962 .

[17]  John K Kruschke,et al.  Bayesian data analysis. , 2010, Wiley interdisciplinary reviews. Cognitive science.

[18]  Jeremy M. G. Taylor.  Power transformations to symmetry , 1985 .

[19]  Ronald E. Glaser,et al.  Bathtub and Related Failure Rate Characterizations , 1980 .

[20]  Adrian F. M. Smith,et al.  Sampling-Based Approaches to Calculating Marginal Densities , 1990 .

[21]  Samuel Kotz,et al.  The Exponentiated Type Distributions , 2006 .

[22]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[23]  Douglas G. Bonett,et al.  Confidence interval for a coefficient of quartile variation , 2006, Comput. Stat. Data Anal..

[24]  B. Jørgensen.  Statistical Properties of the Generalized Inverse Gaussian Distribution , 1981 .

[25]  Helio S. Migon,et al.  Bayesian analysis based on the Jeffreys prior for the hyperbolic distribution , 2012 .

[26]  Standard Probability and Statistics Tables and Formulae , 2001 .

[27]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[28]  J. Moors,et al.  A quantile alternative for kurtosis , 1988 .

[29]  Klaus L. P. Vasconcellos,et al.  Corrected maximum-likelihood estimation in a class of symmetric nonlinear regression models , 2000 .

[30]  Gauss M. Cordeiro,et al.  A generalized modified Weibull distribution for lifetime modeling , 2008 .

[31]  Marc G. Genton,et al.  Multivariate log‐skew‐elliptical distributions with applications to precipitation data , 2009 .

[32]  Narayanaswamy Balakrishnan,et al.  Lifetime analysis based on the generalized Birnbaum-Saunders distribution , 2008, Comput. Stat. Data Anal..

[33]  S. Kotz,et al.  Symmetric Multivariate and Related Distributions , 1989 .

[34]  Wolfgang Hörmann,et al.  Generating generalized inverse Gaussian random variates , 2013, Statistics and Computing.

[35]  Andre Lucas,et al.  Robustness of the student t based M-estimator , 1997 .

[36]  S. Chib,et al.  Understanding the Metropolis-Hastings Algorithm , 1995 .

[37]  Richard A. Groeneveld,et al.  Measuring Skewness and Kurtosis , 1984 .

[38]  Gilberto A. Paula,et al.  Robust statistical modeling using the Birnbaum-Saunders- t distribution applied to insurance , 2012 .

[39]  M. West.  On scale mixtures of normal distributions , 1987 .

[40]  Robert A. Rigby,et al.  Using the Box-Cox t distribution in GAMLSS to model skewness and kurtosis , 2006 .

[41]  W. Stahel,et al.  Log-normal Distributions across the Sciences: Keys and Clues , 2001 .

[42]  Cristian Villegas,et al.  Influence diagnostics in generalized symmetric linear models , 2013, Comput. Stat. Data Anal..