Compstat

1. Front Matter

   Pages I-XI

   PDF

2. Invited Papers

   1. Front Matter

      Pages 1-1

      PDF

   2. An Implementation for Regression Quantile Estimation

      • Thomas W. Yee

      Pages 3-14

   3. Computational Methods for Time Series Analysis

      • Genshiro Kitagawa, Tomoyuki Higuchi, Seisho Sato

      Pages 15-24

   4. Forecasting PC-ARIMA Models for Functional Data

      • Mariano J. Valderrama, Francisco A. Ocaña, Ana M. Aguilera

      Pages 25-36

   5. KyPlot as a Tool for Graphical Data Analysis

      • Koichi Yoshioka

      Pages 37-46

   6. Mice and Elephants Visualization of Internet Traffic

      • J. S. Marron, Felix Hernandez-Campos, F. D. Smith

      Pages 47-54

   7. Relativity and Resolution for High Dimensional Information Visualization with Generalized Association Plots (GAP)

      • Shun-Chuan Chang, Chun-houh Chen, Yueh-Yun Chi, Chih-Wen Ouyoung

      Pages 55-66

   8. Supervised Learning from Microarray Data

      • Trevor Hastie, Robert Tibshirani, Balasubramanian Narasimhan, Gilbert Chu

      Pages 67-77

   9. Teaching Statistics with Electronic Textbooks

      • Jürgen Symanzik, Natascha Vukasinovic

      Pages 79-90

   10. Trans-Dimensional Markov Chains and their Applications in Statistics

       • S. P. Brooks

       Pages 91-102

3. Full Papers

   1. Front Matter

      Pages 103-103

      PDF

   2. A Bayesian Model for Compositional Data Analysis

      • Mark J Brewer, Chris Soulsby, Sarah M Dunn

      Pages 105-110

   3. A Comparison of Marginal Likelihood Computation Methods

      • Charles S. Bos

      Pages 111-116

   4. A Hotelling Test Based on MCD

      • G. Willems, G. Pison, P. J. Rousseeuw, S. Van Aelst

      Pages 117-122

   5. A Resampling Approach to Cluster Validation

      • Volker Roth, Tilman Lange, Mikio Braun, Joachim Buhmann

      Pages 123-128

   6. A Self Documenting Programming Environment for Weighting

      • Wilfried Grossmann, Petra Ofner

      Pages 129-134

   7. A State Space Model for Non-Stationary Functional Data1

      • Mónica Ortega-Moreno, Mariano J. Valderrama, Juan Carlos Ruiz-Molina

      Pages 135-140

   8. A Wildlife Simulation Package (WiSP)

      • Walter Zucchini, Martin Erdelmeier, David Borchers

      Pages 141-146

   9. Algorithmical and Computational Procedures for a Markov Model in Survival Analysis

      • Juan Eloy Ruiz-Castro, Rafael Pérez-Ocón, Delia Montoro-Cazorla

      Pages 147-152

This COMPSTAT 2002 book contains the Keynote, Invited, and Full Contributed papers presented in Berlin, August 2002. A companion volume including Short Communications and Posters is published on CD. The COMPSTAT 2002 is the 15th conference in a serie of biannual conferences with the objective to present the latest developments in Computational Statistics and is taking place from August 24th to August 28th, 2002. Previous COMPSTATs were in Vienna (1974), Berlin (1976), Leiden (1978), Edinburgh (1980), Toulouse (1982), Pra~ue (1984), Rome (1986), Copenhagen (1988), Dubrovnik (1990), Neuchatel (1992), Vienna (1994), Barcelona (1996), Bris­ tol (1998) and Utrecht (2000). COMPSTAT 2002 is organised by CASE, Center of Applied Statistics and Eco­ nomics at Humboldt-Universitat zu Berlin in cooperation with F'reie Universitat Berlin and University of Potsdam. The topics of COMPSTAT include methodological applications, innovative soft­ ware and mathematical developments, especially in the following fields: statistical risk management, multivariate and robust analysis, Markov Chain Monte Carlo Methods, statistics of E-commerce, new strategies in teaching (Multimedia, In­ ternet), computerbased sampling/questionnaires, analysis of large databases (with emphasis on computing in memory), graphical tools for data analysis, classification and clustering, new statistical software and historical development of software.

• Markov Chain
• Mathematica
• STATISTICA
• Statistical Risk Management
• clustering
• data analysis
• statistical software

• CASE — Centre of Applied Statistics and Economics, Humboldt-Universität zu Berlin, Berlin, Germany

  Wolfgang Härdle

• Wirtschaftswissenschaftliche Fakultät, Institut für Statistik und Ökonometrie, Humboldt-Universität zu Berlin, Berlin, Germany

  Bernd Rönz

Policies and ethics