Written for the professional statistician or graduate statistics student, the primary objective of this book is to describe a system, based on the LISP language, for statistical computing and dynamic graphics to show how it can be used as an effective platform for a wide range of statistical computing tasks ranging from basic calculations to customizing dynamic graphs. In addition, it introduces object-oriented programming and graphics programming in a statistical context. The discussion of these ideas is based on the Lisp-Stat system; readers with access to such a system can reproduce the examples presented and use them as a basis for further experimentation and study.
This book assembles papers which were presented at the biennial sympo sium in Computational Statistics held und er the a!uspices of the International Association for Statistical Computing (IASC), a section of ISI, the Interna tional Statistical Institute. This symposium named COMPSTAT '94 was organized by the Statistical Institutes of the University of Vienna and the University of Technology of Vienna, Austria. The series of COMPSTAT Symposia started 1974 in Vienna. Mean while they took place every other year in Berlin (Germany, 1976), Leiden (The Netherlands, 1978), Edinburgh (Great Britain, 1980), Toulouse (France, 1982), Prague (Czechoslovakia, 1984), Rom (Italy, 1986), Copenhagen (Den mark, 1988), Dubrovnik (Yugoslavia, 1990) and Neuchätel (Switzerland, 1992). This year we are celebrating the 20th anniversary in Vienna, Austria. It has obviously been observed a movement from "traditional" computa tional statistics with emphasis on methods which produce results quickly and reliably, to computationally intensive methods like resampling procedures, Bayesian methods, dynamic graphics, to very recent areas like neural net works, accentuation on spatial statistics, huge data sets, analysis strategies, etc. For the organization of the symposium, new guidelines worked out by the IASC in written form were in effect this time. The goal was to refresh somehow the spirit of the start of COMPSTAT '74, keep the tradition of the series and ensure a certain continuity in the sequence of biannual meetings.
The Role of the Computer in Statistics David Cox Nuffield College, Oxford OXIINF, U.K. A classification of statistical problems via their computational demands hinges on four components (I) the amount and complexity of the data, (il) the specificity of the objectives of the analysis, (iii) the broad aspects of the approach to analysis, (ill) the conceptual, mathematical and numerical analytic complexity of the methods. Computational requi rements may be limiting in (I) and (ill), either through the need for special programming effort, or because of the difficulties of initial data management or because of the load of detailed analysis. The implications of modern computational developments for statistical work can be illustrated in the context of the study of specific probabilistic models, the development of general statistical theory, the design of investigations and the analysis of empirical data. While simulation is usually likely to be the most sensible way of investigating specific complex stochastic models, computerized algebra has an obvious role in the more analyti cal work. It seems likely that statistics and applied probability have made insufficient use of developments in numerical analysis associated more with classical applied mathematics, in particular in the solution of large systems of ordinary and partial differential equations, integral equations and integra-differential equations and for the ¢raction of "useful" in formation from integral transforms. Increasing emphasis on models incorporating specific subject-matter considerations is one route to bridging the gap between statistical ana.
Since the beginning of the seventies computer hardware is available to use programmable computers for various tasks. During the nineties the hardware has developed from the big main frames to personal workstations. Nowadays it is not only the hardware which is much more powerful, but workstations can do much more work than a main frame, compared to the seventies. In parallel we find a specialization in the software. Languages like COBOL for business orientated programming or Fortran for scientific computing only marked the beginning. The introduction of personal computers in the eighties gave new impulses for even further development, already at the beginning of the seven ties some special languages like SAS or SPSS were available for statisticians. Now that personal computers have become very popular the number of pro grams start to explode. Today we will find a wide variety of programs for almost any statistical purpose (Koch & Haag 1995).
Modern astronomical research faces a vast range of statistical issues which have spawned a revival in methodological activity among astronomers. The Statistical Challenges in Modern Astronomy II conference brought astronomers and statisticians together to discuss methodological issues of common interest. Time series analysis, image analysis, Bayesian methods, Poisson processes, nonlinear regression, maximum likelihood, multivariate classification, and wavelet and multiscale analyses were all important themes. Many problems were introduced at the conference in the context of large-scale astronomical projects including LIGO, AXAF, XTE, Hipparcos, and digitised sky surveys. As such, this volume will be of interest to researchers and advanced students in both fields - astronomers seeking exposure to recent developments in statistics, and statisticians interested in confronting new problems.
Derived from presentations made at the third annual UK National Conference on GIS Research, this work consists of contributions by leading experts in: geography, mathematics, computing science, surveying, archaeology, planning and medicine.
A visually intuitive approach to statistical data analysis Visual Statistics brings the most complex and advanced statistical methods within reach of those with little statistical training by using animated graphics of the data. Using ViSta: The Visual Statistics System-developed by Forrest Young and Pedro Valero-Mora and available free of charge on the Internet-students can easily create fully interactive visualizations from relevant mathematical statistics, promoting perceptual and cognitive understanding of the data's story. An emphasis is placed on a paradigm for understanding data that is visual, intuitive, geometric, and active, rather than one that relies on convoluted logic, heavy mathematics, systems of algebraic equations, or passive acceptance of results. A companion Web site complements the book by further demonstrating the concept of creating interactive and dynamic graphics. The book provides users with the opportunity to view the graphics in a dynamic way by illustrating how to analyze statistical data and explore the concepts of visual statistics. Visual Statistics addresses and features the following topics: * Why use dynamic graphics? * A history of statistical graphics * Visual statistics and the graphical user interface * Visual statistics and the scientific method * Character-based statistical interface objects * Graphics-based statistical interfaces * Visualization for exploring univariate data This is an excellent textbook for undergraduate courses in data analysis and regression, for students majoring or minoring in statistics, mathematics, science, engineering, and computer science, as well as for graduate-level courses in mathematics. The book is also ideal as a reference/self-study guide for engineers, scientists, and mathematicians. With contributions by highly regarded professionals in the field, Visual Statistics not only improves a student's understanding of statistics, but also builds confidence to overcome problems that may have previously been intimidating.
Revised and updated with the latest results, this Third Edition explores the theory and applications of linear models. The authors present a unified theory of inference from linear models and its generalizations with minimal assumptions. They not only use least squares theory, but also alternative methods of estimation and testing based on convex loss functions and general estimating equations. Highlights of coverage include sensitivity analysis and model selection, an analysis of incomplete data, an analysis of categorical data based on a unified presentation of generalized linear models, and an extensive appendix on matrix theory.
Whether you are a statistician, engineer, or businessperson, you need statistics. You want to be able to easily reference tables, find formulas, and know how to use them so you can extract information from data without getting bogged down by advanced statistical methods. Your goal is to determine the appropriate statistical procedures and interpret the results. Standard Probability and Statistics: Tables and Formulae provides the tools you need to do just that. Logically organized and reaching far beyond a mere catalog, a textual description accompanies each entry- most include an example. The topics addressed are directly applicable to modern business and engineering as well as to statistics, including regression analysis, ANOVA, decision theory, signal processing, and control theory. The result is an accessible, example-oriented handbook that supplies the basic principles, the most commonly used values, and the information to make them work for you. It is easy to fill a statistics reference with hundreds of pages of tables - sometimes for just one test. This handbook is much more. With topics ranging from classical statistics to modern applications, Standard Probability and Statistics fills the need for an up-to-date, authoritative statistics reference.
The Fifth Purdue International Symposium on Statistical Decision The was held at Purdue University during the period of ory and Related Topics June 14-19,1992. The symposium brought together many prominent leaders and younger researchers in statistical decision theory and related areas. The format of the Fifth Symposium was different from the previous symposia in that in addition to the 54 invited papers, there were 81 papers presented in contributed paper sessions. Of the 54 invited papers presented at the sym posium, 42 are collected in this volume. The papers are grouped into a total of six parts: Part 1 - Retrospective on Wald's Decision Theory and Sequential Analysis; Part 2 - Asymptotics and Nonparametrics; Part 3 - Bayesian Analysis; Part 4 - Decision Theory and Selection Procedures; Part 5 - Probability and Probabilistic Structures; and Part 6 - Sequential, Adaptive, and Filtering Problems. While many of the papers in the volume give the latest theoretical developments in these areas, a large number are either applied or creative review papers.
