Statistical inference for models with multivariate t-distributed errors
Introductory exposition (textbooks, tutorial papers, etc.) pertaining to statistics (62-01) Estimation in multivariate analysis (62H12) Linear regression; mixed models (62J05) Ridge regression; shrinkage estimators (Lasso) (62J07) Analysis of variance and covariance (ANOVA) (62J10) Applications of statistics (62Pxx)
The book is related to statistical inference techniques for linear models, in the framework of the analysis of multivariate observations. The key issues addressed by the authors are mainly connected with Student's \(t\)-distribution methods. Starting from some well-known issues in the classical theory based on the normal distribution and a brief review of other known distributions, the book opens subjects as location models, simple regression models, analysis of variance, parallelism models, multiple regression models, ridge regression, multivariate models, Bayesian analysis, linear prediction models and Stein estimation, each of these constituting a chapter from those twelve chapters of the book. NEWLINENEWLINEEach chapter, including the introductory and the preliminary chapters, begins with an overview of the paragraphs and ends with a set of problems which make the book very challenging for the reader. Also, some practical examples from the real world are exposed to illustrate the linear regression models with non-normal errors. NEWLINENEWLINEIn the introductory chapter (Chapter 1), the authors reveal the aim of the book -- the statistical analysis for various linear models with multivariate \(t\)-distribution errors -- being outlined as a comparison between the classical (normal distribution based) approach and the mentioned \(t\)-distribution approach. Subjects as location models, simple and multiple regression models, analysis of variance, parallelism models, ridge regression, multivariate models, are discussed briefly, under the theory of normal distribution. Chapter 2 (``Preliminaries) acts as an introductory chapter too, showing classical properties for the Gaussian and other Gaussian based distributions (Fisher, Student, chi-square) including both univariate and multivariate distribution for normal and \(t\)-Student distribution. The location model under the assumption of the multivariate \(t\)-distribution of the errors is presented in Chapter 3, together with its coefficient estimates and hypothesis testing, including the preliminary test and shrinkage type estimators of the parameters involved. Using the same approach, the authors deal with simple regression models in Chapter 4, ANOVA models in Chapter 5, parallelism models in Chapter 6, multiple regression models respectively ridge regression models in Chapters 7 and 8. Multivariate models together with related statistical inference techniques are discussed in Chapter 9, the Bayesian approach of the multivariate \(t\)-models in Chapter 10, linear prediction models in Chapter 11 and Stein estimation in the last chapter. NEWLINENEWLINEThe book comes with some extra tools for the reader's help such as a list of figures, a list of tables, a glossary for the main concepts used in the book, an author and a subject index, all making the book easily readable.NEWLINENEWLINEThe reference list contains both classical and the cutting edge works in the field. The book is an excellent organized work that can be used both as a textbook for graduate students and researchers and as a guide for the practitioners in the field who need a more rigorous methodology.
- Estimation in multivariate errors-in-variables models
- Statistical Bayesian estimation for multivariate \(T\)-distributions
- Estimation methods for the multivariate \(t\) distribution
- Statistical inference for varying-coefficient models with error-prone covariates
- Estimation in restricted regression model with multivariate-t distributed error
- A generalized class of estimators in linear regression models with multivariate-t distributed error
- Inference in multivariate regression models with measurement errors
- The generalized preliminary test estimator when different sets of stochastic restrictions are available
- Statistical estimation for stationary models with tapered data
- Long-term prediction of the metals' prices using non-Gaussian time-inhomogeneous stochastic process
- Statistical inference for stationary linear models with tapered data
- Improved mixed model for longitudinal data analysis using shrinkage method
- Estimation in the complementary exponential geometric distribution based on progressive type-II censored data
- Interval estimation of parameters in a multivariate t-model with Rao's simple structure
- Conditional inference for treatment and error in multivariate analysis
- Multivariate T-Distributions and Their Applications
- Comparison of preliminary test estimators based on generalized order statistics from proportional hazard family using Pitman measure of closeness
- The distribution of the Liu-type estimator of the biasing parameter in elliptically contoured models
- Shrinkage estimator of regression model under asymmetric loss
- Least-trimmed squares: asymptotic normality of robust estimator in semiparametric regression models
- Inference in multivariate linear regression models with elliptically distributed errors
- Subspace-restricted elastic net estimation: applications in medical data
- A legacy in statistics: the life and contributions of Professor A. K. Md. Ehsanes Saleh
This page was built for publication: Statistical inference for models with multivariate \(t\)-distributed errors
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6486848)
