Proceedings Of The International Conference On Linear Statistical Inference Linstat ?93 (mathematics And Its Applications)

The International Conference on Linear Statistical Inference LINSTAT'93 was held in Poznan, Poland, from May 31 to June 4, 1993. The purpose of the confer­ ence was to enable scientists, from various countries, engaged in the diverse areas of statistical sciences and practice to meet together and exchange views and re­ sults related to the current research on linear statistical inference in its broadest sense. Thus, the conference programme included sessions on estimation, prediction and testing in linear models, on robustness of some relevant statistical methods, on estimation of variance components appearing in linear models, on certain gen­ eralizations to nonlinear models, on design and analysis of experiments, including optimality and comparison of linear experiments, and on some other topics related to linear statistical inference. Within the various sessions 22 invited papers and 37 contributed papers were presented, 12 of them as posters. The conference gathered 94 participants from eighteen countries of Europe, North America and Asia. There were 53 participants from abroad and 41 from Poland. The conference was the second of this type, devoted to linear statistical inference. The first was held in Poznan in June, 4-8, 1984. Both belong to the series of confer­ ences on mathematical statistics and probability theory organized under the auspices of the Committee of Mathematics of the Polish Academy of Sciences, due to the ini­ tiative and efforts of its Mathematical Statistics Section. In the years 1973-1993 there were held in Poland nineteen such conferences, some of them international. Front Matter....Pages i-xviii Increments for (CO)Kriging with Trend and Pseudo-Covariance Estimation....Pages 1-11 On the Representation of the Minimax Linear Estimator in the Convex Linear Model....Pages 13-26 Estimation of Parameters in a Special Type of Random Effects Model....Pages 27-34 Recent Results in Multiple Testing: Several Treatments vs. A Specified Treatment....Pages 35-46 Multiple-Multivariate-Sequential T 2 -Comparisons....Pages 47-51 On Diagnosing Collinearity-Influential Points in Linear Regression....Pages 53-63 Using Nonnegative Minimum Biased Quadratic Estimation for Variable Selection in the Linear Regression Model....Pages 65-71 Partial Least Squares and a Linear Model....Pages 73-78 One-Way Analysis of Variance Under Tukey Contamination: A Small Sample Case Simulation Study....Pages 79-86 A Note on Robust Estimation of Parameters in Mixed Unbalanced Models....Pages 87-95 Optimal Bias Bounds for Robust Estimation in Linear Models....Pages 97-102 Geometrical Relations Among Variance Component Estimators....Pages 103-111 Asymptotic Efficiencies of MINQUE and ANOVA Variance Component Estimates in the Nonnormal Random Model....Pages 113-119 On Asymptotic Normality of Admissible Invariant Quadratic Estimators of Variance Components....Pages 121-127 Admissible Nonnegative Invariant Quadratic Estimation in Linear Models with Two Variance Components....Pages 129-137 About the Multimodality of the Likelihood Function when Estimating the Variance Components in a One-Way Classification by Means of the Ml or REML Method....Pages 139-146 Prediction Domain in Nonlinear Models....Pages 147-158 The Geometry of Nonlinear Inference: Accounting of Prior and Boundaries....Pages 159-170 General Balance: Artificial Theory or Practical Relevance?....Pages 171-184 Optimality of Generally Balanced Experimental Block Designs....Pages 185-194 Optimality of the Orthogonal Block Design for Robust Estimation under Mixed Models....Pages 195-202 On Generalized Binary Proper Efficiency-Balanced Block Designs....Pages 203-210 Design of Experiments and Neighbour Methods....Pages 211-221 A New Look into Composite Designs....Pages 223-228 Using the Complex Linear Model to Search for an Optimal Juxtaposition of Regular Fractions....Pages 229-237 Some Directions in Comparison of Linear Experiments: A Review....Pages 239-244 Properties of Comparison Criteria of Normal Experiments....Pages 245-253 Characterizations of Oblique and Orthogonal Projectors....Pages 255-270 Asymptotic Properties of Least Squares Parameter Estimators in a Dynamic Errors-in-Variables Model....Pages 271-283 A Generic Look at Factor Analysis....Pages 285-291 On Q-Covariance and its Applications....Pages 293-300 Back Matter....Pages 301-306 This volume contains a selection of invited and contributed papers presented at the International Conference on Linear Statistical Inference LINSTAT '93, held in Poznan, Poland, from May 31 to June 4, 1993. Topics treated include estimation, prediction and testing in linear models, robustness of relevant statistical methods, estimation of variance components appearing in linear models, generalizations to nonlinear models, design and analysis of experiments, including optimality and comparison of linear experiments. This book will be of interest to mathematical statisticians, applied statisticians, biometricians, biostatisticians, and econometrists. These proceedings detail topics, including estimation, prediction and testing in linear models, robustness of relevant statistical methods, estimation of variance components appearing in linear models, design and analysis of experiments.