Recent Advances in Linear Models and Related Areas

This collection contains invited papers by distinguished statisticians to honour and acknowledge the contributions of Professor Dr. Dr. Helge Toutenburg to Statistics on the occasion of his sixty-?fth birthday. These papers present the most recent developments in the area of the linear model and its related topics. Helge Toutenburg is an established statistician and currently a Professor in the Department of Statistics at the University of Munich (Germany) and Guest Professor at the University of Basel (Switzerland). He studied Mathematics in his early years at Berlin and specialized in Statistics. Later he completed his dissertation (Dr. rer. nat. ) in 1969 on optimal prediction procedures at the University of Berlin and completed the post-doctoral thesis in 1989 at the University of Dortmund on the topic of mean squared error superiority. He taught at the Universities of Berlin, Dortmund and Regensburg before joining the University of Munich in 1991. He has various areas of interest in which he has authored and co-authored over 130 research articles and 17 books. He has made pioneering contributions in several areas of statistics, including linear inference, linear models, regression analysis, quality engineering, Taguchi methods, analysis of variance, design of experiments, and statistics in medicine and dentistry.

Includes supplementary material: sn.pub/extras

Autorentext
Christian Heumann studierte (1987-1992) Diplom-Statistik, promovierte 1997 und habilitierte 2004 an der Ludwig-Maximilians-Universität München. Er forscht und publiziert u.a. über fehlende Daten, Modelle für korrelierte kategoriale Daten und Rater-Agreement-Modelle.

Klappentext

The theory of linear models and regression analysis plays an essential role in the development of methods for the statistical modelling of data.

The book presents the most recent developments in the theory and applications of linear models and related areas of active research. The contributions include topics such as boosting, Cox regression models, cluster analysis, design of experiments, feasible generalized least squares, information theory, matrix theory, measurement error models, missing data models, mixture models, panel data models, penalized least squares, prediction, regression calibration, spatial models and time series models.

Several contributions illustrate applications in biomedical research, economics, finance, genetic epidemiology and medicine.

Inhalt
On the Identification of Trend and Correlation in Temporal and Spatial Regression.- Estimating the Number of Clusters in Logistic Regression Clustering by an Information Theoretic Criterion.- Quasi Score and Corrected Score Estimation in the Polynomial Measurement Error Model.- Estimation and Finite Sample Bias and MSE of FGLS Estimator of Paired Data Model.- Prediction of Finite Population Total in Measurement Error Models.- The Vector Cross Product and 4 × 4 Skew-symmetric Matrices.- Simultaneous Prediction of Actual and Average Values of Response Variable in Replicated Measurement Error Models.- Local Sensitivity in the Inequality Restricted Linear Model.- Boosting Correlation Based Penalization in Generalized Linear Models.- Simultaneous Prediction Based on Shrinkage Estimator.- Finite Mixtures of Generalized Linear Regression Models.- Higher-order Dependence in the General Power ARCH Process and the Role of Power Parameter.- Regression Calibration for Cox Regression Under Heteroscedastic Measurement Error Determining Risk Factors of Cardiovascular Diseases from Error-prone Nutritional Replication Data.- Homoscedastic Balanced Two-fold Nested Model when the Number of Sub-classes is Large.- QR-Decomposition from the Statistical Point of View.- On Penalized Least-Squares: Its Mean Squared Error and a Quasi-Optimal Weight Ratio.- Optimal Central Composite Designs for Fitting Second Order Response Surface Linear Regression Models.- Does Convergence Really Matter?.- OLS-Based Estimation of the Disturbance Variance Under Spatial Autocorrelation.- Application of Self-Organizing Maps to Detect Population Stratification.- Optimal Designs for Microarray Experiments with Biological and Technical Replicates.- Weighted Mixed Regression Estimation Under Biased StochasticRestrictions.- Coin Tossing and Spinning Useful Classroom Experiments for Teaching Statistics.- Linear Models in Credit Risk Modeling.