Moments and random number generation for the truncated elliptical family of distributions

This paper proposes an algorithm to generate random numbers from any member of the truncated multivariate elliptical family of distributions with a strictly decreasing density generating function. Based on Neal (2003) and Ho et al. (2012), we construct an efficient sampling method by means of a slice sampling algorithm with Gibbs sampler steps. We also provide a faster approach to approximate the first and the second moment for the truncated multivariate elliptical distributions where Monte Carlo integration is used for the truncated partition, and explicit expressions for the non-truncated part (Galarza et al., 2020). Examples and an application to environmental spatial data illustrate its usefulness. Methods are available for free in the new R library relliptical.

[1]  Jose A. Ordonez,et al.  Geostatistical estimation and prediction for censored responses. , 2018, Spatial statistics.

[2]  Victor H. Lachos,et al.  Moments of the doubly truncated selection elliptical distributions with emphasis on the unified multivariate skew-t distribution , 2020, J. Multivar. Anal..

[3]  John Zirschky,et al.  Geostatistical Analysis of Hazardous Waste Site Data , 1986 .

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

[5]  C. E. Galarza,et al.  On moments of folded and truncated multivariate Student-t distributions based on recurrence relations , 2021 .

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

[7]  C. E. Galarza,et al.  Finite mixture modeling of censored and missing data using the multivariate skew-normal distribution , 2020, Advances in Data Analysis and Classification.

[8]  D. Dittmar.  Slice Sampling , 2000 .

[9]  Ming-Hui Chen,et al.  Flexible longitudinal linear mixed models for multiple censored responses data , 2018, Statistics in medicine.

[10]  A skew‐t quantile regression for censored and missing data , 2021, Stat.

[11]  P. Dixon,et al.  Data augmentation for a Bayesian spatial model involving censored observations , 2007 .

[12]  P. Diggle,et al.  Model‐based geostatistics , 2007 .

[13]  V. H. Lachos,et al.  Censored mixed-effects models for irregularly observed repeated measures with applications to HIV viral loads , 2016 .

[14]  Ming-Hui Chen,et al.  Likelihood-based Inference For Mixed-effects Models With Censored Response Using The Multivariate-t Distribution , 2013 .

[15]  M. A. Gómez–Villegas,et al.  A MATRIX VARIATE GENERALIZATION OF THE POWER EXPONENTIAL FAMILY OF DISTRIBUTIONS , 2002 .

[16]  D. Anderson,et al.  Algorithms for minimization without derivatives , 1974 .

[17]  Aldo M. Garay,et al.  Influence diagnostics in spatial models with censored response , 2017 .

[18]  Tsung-I Lin,et al.  Some results on the truncated multivariate t distribution , 2012 .

[19]  G. C. Wei,et al.  A Monte Carlo Implementation of the EM Algorithm and the Poor Man's Data Augmentation Algorithms , 1990 .

[20]  É. Moulines,et al.  Convergence of a stochastic approximation version of the EM algorithm , 1999 .

[21]  S. Ferrari,et al.  New Results on Truncated Elliptical Distributions , 2019, Communications in Mathematics and Statistics.

[22]  R. Muirhead.  Aspects of Multivariate Statistical Theory , 1982, Wiley Series in Probability and Statistics.

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

[24]  Adrian F. M. Smith,et al.  Bayesian Analysis of Constrained Parameter and Truncated Data Problems , 1991 .

[25]  Christian P. Robert,et al.  Introducing Monte Carlo Methods with R , 2009 .

[26]  Raymond Kan,et al.  On Moments of Folded and Truncated Multivariate Normal Distributions , 2016 .