Claus Weihs – författare

A new and refreshingly different approach to presenting the foundations of statistical algorithms, Foundations of Statistical Algorithms: With References to R Packages reviews the historical development of basic algorithms to illuminate the evolution of today’s more powerful statistical algorithms. It emphasizes recurring themes in all statistical algorithms, including computation, assessment and verification, iteration, intuition, randomness, repetition and parallelization, and scalability. Unique in scope, the book reviews the upcoming challenge of scaling many of the established techniques to very large data sets and delves into systematic verification by demonstrating how to derive general classes of worst case inputs and emphasizing the importance of testing over a large number of different inputs. Broadly accessible, the book offers examples, exercises, and selected solutions in each chapter as well as access to a supplementary website. After working through the material covered in the book, readers should not only understand current algorithms but also gain a deeper understanding of how algorithms are constructed, how to evaluate new algorithms, which recurring principles are used to tackle some of the tough problems statistical programmers face, and how to take an idea for a new method and turn it into something practically useful.

This book provides a comprehensive overview of music data analysis, from introductory material to advanced concepts. It covers various applications including transcription and segmentation as well as chord and harmony, instrument and tempo recognition. It also discusses the implementation aspects of music data analysis such as architecture, user interface and hardware. It is ideal for use in university classes with an interest in music data analysis. It also could be used in computer science and statistics as well as musicology.

This Element introduces PrInDT (Prediction and Interpretation in Decision Trees), a statistical approach for modeling relationships between extra- and intralinguistic variables in World Englishes. It is based on decision trees and controls their size in a way that they are easy and straightforward to interpret. Furthermore, PrInDT optimizes their accuracy so that they best fit the data and can be reliably used for prediction. Moreover, it can handle unbalanced classes that occur, for example, when comparing non-standard with standard linguistic realizations. The various PrInDT functions can deal with classification and regression tasks and can analyze multiple endogenous variables jointly, even for models combining classification and regression. The authors introduce these features in some detail and apply them to World Englishes and sociolinguistic datasets. As examples, they draw on L1 child data from England and Singapore as well as linguistic landscapes data from the Eastern Caribbean island of St. Martin.

This Element introduces PrInDT (Prediction and Interpretation in Decision Trees), a statistical approach for modeling relationships between extra- and intralinguistic variables in World Englishes. It is based on decision trees and controls their size in a way that they are easy and straightforward to interpret. Furthermore, PrInDT optimizes their accuracy so that they best fit the data and can be reliably used for prediction. Moreover, it can handle unbalanced classes that occur, for example, when comparing non-standard with standard linguistic realizations. The various PrInDT functions can deal with classification and regression tasks and can analyze multiple endogenous variables jointly, even for models combining classification and regression. The authors introduce these features in some detail and apply them to World Englishes and sociolinguistic datasets. As examples, they draw on L1 child data from England and Singapore as well as linguistic landscapes data from the Eastern Caribbean island of St. Martin.

This book provides a comprehensive overview of music data analysis, from introductory material to advanced concepts. It covers various applications including transcription and segmentation as well as chord and harmony, instrument and tempo recognition. It also discusses the implementation aspects of music data analysis such as architecture, user interface and hardware. It is ideal for use in university classes with an interest in music data analysis. It also could be used in computer science and statistics as well as musicology.

This volume presents theoretical developments, applications and computational methods for the analysis and modeling in behavioral and social sciences where data are usually complex to explore and investigate. The challenging proposals provide a connection between statistical methodology and the social domain with particular attention to computational issues in order to effectively address complicated data analysis problems.The papers in this volume stem from contributions initially presented at the joint international meeting JCS-CLADAG held in Anacapri (Italy) where the Japanese Classification Society and the Classification and Data Analysis Group of the Italian Statistical Society had a stimulating scientific discussion and exchange.

This volume contains revised versions of selected papers presented during the 28th Annual Conference of the Gesellschaft fur .. Klassi?kation (GfKl), the German Classi?cation Society. The conference was held at the Universit. at Dortmund in Dortmund, Germany, in March 2004. Wolfgang Gaul chaired the program committee, Claus Weihs and Ernst-Erich Doberkat were the local organizers. Patrick Groenen, Iven van Mechelen, and their colleagues of the Vereniging voor Ordinatie en Classi?catie (VOC), the Dutch-Flemish Classi?cation Society, organized special VOC sessions. The programcommittee recruited17 notable and internationallyreno- ed invited speakers for plenary and semi-plenary talks on their current - search work regarding classi?cation and data analysis methods as well as - plications.Inaddition,172invitedandcontributedpapersbyauthorsfrom18 countrieswerepresentedatthe conferencein 52parallelsessionsrepresenting the whole ?eld addressed by the title of the conference "Classi?cation: The Ubiquitous Challenge". Among these 52 sessions the VOC organizedsessions on Mixture Modelling, Optimal Scaling, Multiway Methods, and Psychom- ricswith18papers.Overall,theconference,whichistraditionallydesignedas an interdisciplinary event, again provided an attractive forum for discussions and mutual exchange of knowledge.Besides the results obtained in the fundamental subjects Classi?cation and Data Analysis, the talks in the applied areas focused on various app- cation topics. Moreover, along with the conference a competition on "Social Milieus in Dortmund", co-organized by the city of Dortmund, took place. Hence the presentation of the papers in this volume is arranged in the f- lowing parts: I. (Semi-)Plenary Presentations II. Classi?cation and Data Analysis III. Applications, and IV. Contest: Social Milieus in Dortmund.

Clustering and Classification, Data Analysis, Data Handling and Business Intelligence are research areas at the intersection of statistics, mathematics, computer science and artificial intelligence. They cover general methods and techniques that can be applied to a vast set of applications such as in business and economics, marketing and finance, engineering, linguistics, archaeology, musicology, biology and medical science. This volume contains the revised versions of selected papers presented during the 11th Biennial IFCS Conference and 33rd Annual Conference of the German Classification Society (Gesellschaft für Klassifikation - GfKl). The conference was organized in cooperation with the International Federation of Classification Societies (IFCS), and was hosted by Dresden University of Technology, Germany, in March 2009.

Dieser Sammelband zeigt an ausgewählten Beispielen, wie spannend und vielfältig statistische Forschung sein kann. Ob es nun darum geht, hörgeschädigten Menschen einen guten Musikgenuss zu verschaffen, aus Texten sinnvolle quantitative Daten zu extrahieren oder Überschwemmungskatastrophen zu modellieren und damit besser in den Griff zu bekommen – die meisten in diesem Buch dargestellten Erkenntnisse sind nicht in Lehrbüchern zu finden, sie stammen direkt von der Forschungsfront und laden zum Staunen und Entdecken ein.Auf Fachjargon und Formalismus wird bei der Darstellung so weit wie möglich verzichtet – das Buch richtet sich somit an jeden, der sich für das aktuelle Forschungsgeschehen im Bereich statistischer Anwendungen interessiert. Es ermöglicht einen unverdeckten Blick auf eine durch und durch faszinierende Wissenschaft – ohne dass die einzelnen Analysen bis ins Detail nachvollzogen werden müssen. Studierenden kann das Buch helfen, Begeisterung für statistische Fragestellungen und Methoden zu entwickeln, oder sogar Anregungen für die eigene Laufbahn geben.Ein Großteil der Beiträge entstand an der Fakultät Statistik der TU Dortmund, der einzigen eigenständigen Statistik-Fakultät im ganzen deutschen Sprachgebiet, sowie darüber hinaus im Rahmen von an diese Fakultät angedockten DFG-Sonderforschungsbereichen.

Dieses Buch zeigt anhand von journalistischen Fallbeispielen, warum und wie fortgeschrittene statistische Analysemethoden eingesetzt werden können, um aussagekräftige journalistische Informationen aus Daten zu extrahieren. Gleichzeitig setzt das Buch einen Anforderungsrahmen für die datenjournalistische Arbeit bezüglich Datenkompetenz und -visualisierung, dem Einsatz von Algorithmen sowie daten-ethischen Anforderungen und der Überprüfung externer Studien.Ziel ist es, die Qualität und Aussagekraft datenjournalistischer Arbeiten zu verbessern, welche, neben der angemessenen Erfassung und Aufbereitung von Daten, wesentlich von einer adäquaten Datenanalyse abhängen. Aber wie statistisch arbeiten Datenjournalist:innen heute eigentlich? Und wie statistisch können oder sollten sie arbeiten, um den Ansprüchen ihrer Leserschaft in Sachen Verständlichkeit gerecht zu werden, auch mit Blick auf deren unterschiedliches mathematisch-statisches Vorwissen? Das Buch zielt darauf ab, diese Fragen zu beantworten, indem es weiterführende statistische Methoden anhand von Fallstudien untersucht. Es verdeutlicht, warum diese Methoden auch im journalistischen Kontext oftmals problemangemessener sind und tiefer gehende Erkenntnisse liefern als vereinfachte Analysen und Basismethoden. Die Fallstudien decken dabei die wichtigsten statistischen Methoden ab: Verteilungen und Tests, Klassifikation, Regression, Zeitreihenanalyse, Clusteranalyse, Analyse von sequentiellen Daten ohne direkten Zeitbezug, Verwendung von Vorwissen und geplante Studien.

This book offers a broad selection of statistical applications to everyday situations, illustrating how exciting and diverse statistical analysis can be.

This book offers a broad selection of statistical applications to everyday situations, illustrating how exciting and diverse statistical analysis can be. It covers a wide variety of topics, including offering hearing-impaired people the option to enjoy music, extracting meaningful quantitative data from texts, and modeling flood disasters to help get a better grip on them. Most of the examples are not typically found in textbooks but directly relate to real-life problems encountered by the “average person”, including topics relevant for sustainable development.Technical jargon and formalism have been avoided as much as possible, and a detailed statistical background is not assumed of the reader, making the book accessible to anyone interested in current research in statistical applications. Providing an unobscured look at a thoroughly fascinating science, it will help students to develop enthusiasm for statistical issues and methods, and may even inspire ideas for their own projects.

Größe und Komplexität empirischer ökonometrischer Modelle haben in den letzten Jahrzehnten immer mehr zugenommen. Die Zuverlässigkeit des zugrundeliegenden Datenmaterials hat sich dagegen kaum verbessert, und eine Fehlspezifizierung von Meßfehlermodellen zur Schließung der Lücke zwischen theoretischen ökonomischen Variablen und den verfügbaren Daten erscheint schon wegen der unglücklichen Trennung zwischen Datenproduzenten und Datennutzern kaum vermeidbar. In dieser Arbeit werden die Auswirkungen solcher Fehlspezifizierungen auf Parameterschätzungen und Prognosen in Modellen wachsender Komplexität bis hin zu nichtlinearen interdependenten dynamischen Modellen analysiert mit Hilfe von asymptotischen Aussagen und Monte-Carlo-Simulationen. Für ein makroökonomisches Modell für die BRD werden außerdem Methoden diskutiert zur Beschaffung von Informationen über Art und Größe von Meßfehlern. Die Simulationsrechnungen basieren auf der Zuverlässigkeit und Schnelligkeit des zugrundeliegenden numerischen Algorithmus zur Full-Information-Maximum-Likelihood-Schätzung in nichtlinearen interdependenten Modellen. Darstellung und Diskussion eines für diesen Zweck entwickelten Algorithmus (trust-region-Verfahren mit automatischer Skalierung) bilden den zweiten Schwerpunkt der Arbeit.