Advances in Shrinkage and Penalized Estimation Strategies

Honoring the Contributions of Professor A. K. Md. Ehsanes Saleh
Erscheinungsjahr 2026
ISBN: 978-3-031-94049-1
Verlag: Springer

Buch, Englisch, 657 Seiten, Format (B × H): 160 mm x 241 mm, Gewicht: 1183 g

Reihe: Emerging Topics in Statistics and Biostatistics

This book is a tribute to Professor A. K. Md. Ehsanes Saleh, a distinguished figure in the field of statistics known for his pioneering work, including the development of the "Preliminary Test Approach to Shrinkage Estimation". Although Professor Saleh passed away in September 2023, his legacy will live on through this special volume that explores penalized approaches for statistical analysis and recent developments in shrinkage methods. Covering regression modeling, robust estimation, machine learning, and high-dimensional data analytics, this volume bridges theoretical advancements with practical applications of these methodologies.

In addition to introducing novel research and viewpoints, the book seeks to encourage dialogue among experienced practitioners in the field. This resource is specifically designed for researchers, statisticians, or data science professionals seeking ways to improve their comprehension and application of these methods.

Zielgruppe

Research

Autoren/Hrsg.

Arashi, Mohammad

Norouzirad, Mina

Fachgebiete

• Mathematik | Informatik Mathematik Stochastik

Inhaltsverzeichnis

Part I Shrinkage Estimation Strategies.- Chapter 1 Restricted Liu-Type Regression Estimators in Linear Regression Model.- Chapter 2 Shrinkage Strategies for Right-Censored Bell Regression Model with Application.- Chapter 3 On a Class of Shrinkage Estimators of Normal Mean in High-dimensional Data with Unknown Covariance.- Chapter 4 Some Stein-rules Methods in Tensor Regression Model with High-Dimensional Data.- Chapter 5 Some Implications of Preliminary-Test Estimation in the Context of Size-Biased Sampling.- Chapter 6 Study the Performance of New Shrinkage Estimators under the Balanced Loss Function.- Chapter 7 Shrinkage Estimators of the Location Parameter Under Modified Balanced Loss Functions.- Chapter 8 Shrinkage Strategies and Superefficiency.- Chapter 9 Shrinkage Estimation of Restricted Mean Vector Under Balanced Loss with Application inWavelet Denoising.- Chapter 10 On Minimaxity of Shrinkage Estimators Under Concave Loss.- Part II Penalized Estimation and Variable Selection.- Chapter 11 Improved LASSO Estimator in Semiparametric Linear Measurement Error Models.- Chapter 12 Weighted-Average Least Squares Estimation of Panel Data Models.- Chapter 13 Performance of Some Test Statistics for Testing the Regression Coefficients for the One and Two Parameters Multicollinear Gaussian Multiple Linear Regression Models: An Empirical Comparison.- Chapter 14 Ineffectiveness of Model Selection via t-Test in Regression with Collinearity.- Chapter 15 A New Ridge-Based Biased Prediction Technique in Linear Mixed Models.- Chapter 16 L-Estimation of Location: Shrinkage and Selection.- Chapter 17 Variable Selection in Regression Models with Dependent and Asymmetrically Distributed Error Term.- Part III Robust Estimation and Nonparametrics Methods.- Chapter 18 Shrinkage Estimator for Spatial Autoregressive Model with Endogenous Covariates.- Chapter 19 Regularization of Robust Neural Networks: Bayesian Connections and Outlier Detection.- Chapter 20 Estimating Finite Mixture Models Using Component Self-Paced Learning.- Chapter 21 Shrinkage Estimation in Generalized CIR Processes with Change-point.- Chapter 22 Estimating and Pretesting in Additive Censored Models.- Chapter 23 Confidence Interval for a Univariate Normal Mean Based on a Pretest Estimator.- Chapter 24 Prediction of Interruptions in Energy Supply: A Machine Learning Study with Post-Shrinkage Modeling.

Über Autor(innen)

Mohammad Arashi is a Full Professor at Ferdowsi University of Mashhad, Iran and Extraordinary Professor and C2 rate researcher at University of Pretoria, South Africa. He has won several prestigious (inter)national awards and has published over 165 articles in accredited journals and co-authored 5 books. His research interest include Shrinkage and Penalized Estimation, High-Dimensional Analysis, Nonparametric Statistics, and Distribution Theory. He is an International Statistical Institute elected member.

Mina Norouzirad is a researcher in Statistics at the Center for Mathematics and Applications (NovaMath), holding a Ph.D. from Shahrood University of Technology, Iran. Previously, she served as a Postdoctoral Fellow at NovaMath, Universidade NOVA de Lisboa, Portugal. Dr. Norouzirad has authored several peer-reviewed publications and co-authored 1 book. Her expertise centers on innovative methodologies for statistical modeling, specializing in Shrinkage, Robust Regression, High-dimensional Analysis, and Machine Learning.