Using mixtures in seemingly unrelated linear regression models with non-normal errors

被引：10

作者：

Galimberti, Giuliano ^{[1
]}

Scardovi, Elena ^{[1
]}

Soffritti, Gabriele ^{[1
]}

机构：

[1] Univ Bologna, Dept Stat Sci, Via Belle Arti 41, I-40126 Bologna, Italy

来源：

STATISTICS AND COMPUTING | 2016年 / 26卷 / 05期

关键词：

EM algorithm; Gaussian mixture model; Hessian matrix; Score vector; LEAST-SQUARES ESTIMATORS; DIRECT MONTE-CARLO; MAXIMUM-LIKELIHOOD; BAYESIAN-ANALYSIS; PREDICTION; EQUATIONS; INFERENCE; SELECTION;

D O I：

10.1007/s11222-015-9587-0

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

Seemingly unrelated linear regression models are introduced in which the distribution of the errors is a finite mixture of Gaussian distributions. Identifiability conditions are provided. The score vector and the Hessian matrix are derived. Parameter estimation is performed using the maximum likelihood method and an Expectation-Maximisation algorithm is developed. The usefulness of the proposed methods and a numerical evaluation of their properties are illustrated through the analysis of simulated and real datasets.

引用

页码：1025 / 1038

页数：14

共 50 条

[1] Using mixtures in seemingly unrelated linear regression models with non-normal errors
Giuliano Galimberti
Elena Scardovi
Gabriele Soffritti
[J]. Statistics and Computing, 2016, 26 : 1025 - 1038
[2] LINEAR REGRESSION WITH NON-NORMAL ERRORS
Li, Na
Vrbik, Jan
[J]. ADVANCES AND APPLICATIONS IN STATISTICS, 2018, 53 (02) : 153 - 164
[3] Bayesian variable selection in linear regression models with non-normal errors
Ranciati, Saverio
Galimberti, Giuliano
Soffritti, Gabriele
[J]. STATISTICAL METHODS AND APPLICATIONS, 2019, 28 (02): : 323 - 358
[4] Bayesian variable selection in linear regression models with non-normal errors
Saverio Ranciati
Giuliano Galimberti
Gabriele Soffritti
[J]. Statistical Methods & Applications, 2019, 28 : 323 - 358
[5] The use of mixtures for dealing with non-normal regression errors
Bartolucci, F
Scaccia, L
[J]. COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2005, 48 (04) : 821 - 834
[6] Multivariate linear regression with non-normal errors: a solution based on mixture models
Gabriele Soffritti
Giuliano Galimberti
[J]. Statistics and Computing, 2011, 21 : 523 - 536
[7] Multivariate linear regression with non-normal errors: a solution based on mixture models
Soffritti, Gabriele
Galimberti, Giuliano
[J]. STATISTICS AND COMPUTING, 2011, 21 (04) : 523 - 536
[8] Linear regression models for heteroscedastic and non-normal data
Thinh, Raksmey
Samart, Klairung
Jansakul, Naratip
[J]. SCIENCEASIA, 2020, 46 (03): : 353 - 360
[9] COMPUTATION OF STANDARD ERRORS IN SEEMINGLY UNRELATED REGRESSION EQUATION MODELS
SRIVASTAVA, AK
TRACY, DS
[J]. COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, 1986, 15 (12) : 3583 - 3588
[10] Seemingly unrelated regression models
Kubacek, Lubomir
[J]. APPLICATIONS OF MATHEMATICS, 2013, 58 (01) : 111 - 123

← 1 2 3 4 5 →