dear sir
i want to be unsubscribed from this service.
thankyou
[log in to unmask] wrote:
> Subjects of messages in this digest:
>
> New titles in Medical Statistics from Arnold Publishers
> ASMT'2001, Prague, June 6-9, 2001
> lecturer position in Belgium
> TALK: RSS Med Sect Tues 28th Nov 3pm @ RSS London
> ADMIN: Mailbase to JISCmail changeover
> new modelling short course
> RSS East Midlands - November Meeting cancelled
> SIAP meeting: 6/12/00
> repeatability and reproducibility
> QUERY: 2 bootstrap questions
> Biostatistics@Keele Reminder
> QUERY : 2 BOOTSTRAP Questions
> ADMIN: Allstat on JISCmail Introduction
> JOB: Chair of Statistical Epidemiology at Leeds University, UK
> ISAS 2001, Last Call for Papers
>
> ----------------------------------------------------------------------
>
> Date: Fri, 24 Nov 2000 09:15:34 -0000
> From: "Ewan Crawford" <[log in to unmask]>
> To: <[log in to unmask]>
> Subject: New titles in Medical Statistics from Arnold Publishers
> Message-Id: <[log in to unmask]>
>
> I've been asked to forward this list of these latest titles in medical
> statistics.
>
> Ewan Crawford
>
> ----- Original Message -----
>
> From: Kathryn Cousins <[log in to unmask]>
>
> New titles:
>
> Statistics in Management Science by Andrew Metcalfe - £35.00 : 0-340-74075-2
> *Includes recent applied work using stochastic processes, useful in
> business forecasting
> http://www.arnoldpublishers.co.uk/scripts/webbook.asp?isbn=0340740752
>
> Statistics in Finance by David Hand and Saul Jacka - £40.00 : 0-340-67719-8
> *Concentrates on the statistics of finance & is expository rather than
> research-based
> http://www.arnoldpublishers.co.uk/scripts/webbook.asp?isbn=0340677198
>
> Introduction to Randomized Controlled Clinical Trials by J. Matthews -
> £19.99 : 0-340-76143-1
> *The first book to introduce the statistical side of clinical trials to
> medical students
> http://www.arnoldpublishers.co.uk/Scripts/webbook.asp?isbn=0340761431
>
> Design and Analysis of Cluster Randomization Trials in Health Research by
> Allan Donner and Neil Klar - £35.00 : 0-340-69153-0
> *Presents methods that are appropriate to cluster randomization design and
> discusses the related issues, such as ethics and informed consent
> http://www.arnoldpublishers.com/Scripts/webbook.asp?isbn=0340691530
>
> Statistical Analysis of Medical Data by Brian Everitt and Graham Dunn -
> £29.99 : 0-340-67775-9
> *Explores areas of new research and emphasises the applications of new
> methodologies
> http://www.arnoldpublishers.com/Scripts/webbook.asp?isbn=0340677759
>
> Applied Multivariate Data Analysis, 2ed by Brian Everitt and Graham Dunn -
> £24.99 : 0-340-74122-8
> *Contains new sections on topical areas such as neural networks and
> hierarchical networking
> http://www.arnoldpublishers.com/Scripts/webbook.asp?isbn=0340741228
>
> *************************************
>
> Arnold
> 338 Euston Road
> London
> NW1 3BH
> UK
>
> *************************************
>
> ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
> Dr Ewan Crawford
> Allstat list owner
> LTSN Maths, Stats & O.R. Centre
> Department of Statistics Phone : +44 (0)141 330 4873
> University of Glasgow Fax : +44 (0)141 330 4814
> ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
> [log in to unmask] http://www.stats.gla.ac.uk/allstat
> ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
>
> ------------------------------
>
> Date: Fri, 24 Nov 2000 12:06:21 +0200
> From: Vladimir Anisimov <[log in to unmask]>
> To: Allstat <[log in to unmask]>
> Subject: ASMT'2001, Prague, June 6-9, 2001
> Message-Id: <[log in to unmask]>
>
> Dear ALL-STAT members,
>
> Would you please distribute the information about the
> 8th International Conference on
> ANALYTICAL and STOCHASTIC MODELLING TECHNIQUES
> (ASMT'2001) Prague (Czech Republic), June 6-9, 2001,
> attached below, among your colleagues especially young researchers
> and people you think might be interested.
> Thanks in advance for your valuable cooperation.
> With best regards,
>
> Vladimir Anisimov
> --------------------------------------
> FIRST CALL FOR PAPERS
>
> 8th International Conference on
>
> ANALYTICAL and STOCHASTIC MODELLING TECHNIQUES
> ( ASMT'2001 )
> Prague (Czech Republic), June 6-9, 2001
>
> Conference is organized by SCS
> (The Society for Computer Simulation International)
> as a part of the
> 15th European Simulation Multiconference
> Prague, Czech Republic
> June 6-9, 2001
> URL: http://hobbes.rug.ac.be/~scs/conf/esm2001/
>
> MOTIVATION:
>
> This Conference is a continuation of series of Conferences in
> Analytical, Numerical and Stochastic Modeling Techniques held as
> a part of European Simulation Conferences.
> Taking into account the complexity of real models of complex
> technical and information systems, methods of stochastic modelling
> based on analytical and approximate results for Markov and
> semi-Markov stochastic processes, queueing networks, Petri nets,
> etc. have recently become increasingly popular.
> In many fields of applications involving performance and
> reliability modelling of discrete flow systems, such as computer
> systems, high speed communication networks, flexible manufacturing
> systems and workflow management systems, it has been widely
> recognized that analytical and approximate approaches in stochastic
> modeling can successfully complement simulation methods.
> There are still many important and interesting problems to be
> resolved such as those involving stochastic Petri nets and queueing
> networks with complex structure, multiple job classes under various
> blocking mechanisms and synchronization constrains, problems of
> self-organization in neuron networks, etc. In these and many other
> models methods based on analytical or approximate analytical
> results are in general more preferable comparatively to methods
> of direct stochastic simulation, because in general they save the
> time of computation and give possibility to obtain analytical
> dependencies of parameters.
>
> Contributions based on analytical, stochastic and approximate
> methods in modelling as well as applications are encouraged but
> not restricted to the following topics:
>
> Topics:
>
> * Techniques and Algorithms:
>
> - Stochastic Models, Markov Models
> - Stochastic Petri Net Models
> - Queueing Systems and Network Models
> - Neuron Networks
> - Reliability and Maintenance Models
> - Stochastic Optimal Control and Optimization
> - Performance Modeling
> - Stochastic Process Algebras
> - Stochastic Precedence Graphs
> - Stochastic Simulation
> - Analytical and Numerical Simulation
>
> * Evaluation Studies of:
>
> - Computer Systems and Information Networks
> - Workflow Management Systems
> - Communication Systems (LANs and Distributed
> Systems, ATM Switches, Mobile Radio,)
> - Workload Modelling and Characterization
> - Operating Systems
> - Client-Server Systems
> - Multimedia Systems
> - Measurements and Hybrid Techniques
> - Software Performance
>
> * Software Tools
>
> ------------------------------------------
>
> CONFERENCE CHAIR:
>
> Dr. Gunter Bolch
> University of Erlangen-Nurenberg
> Department of Computer Science
> Martensstrasse 1, 91058 Erlangen, Germany
> Tel: +49.9131.857903, Fax: +49.9131.39388
> E-mail: [log in to unmask]
> URL: http://www4.informatik.uni-erlangen.de/~bolch
>
> PROGRAM CHAIR:
>
> Prof. Vladimir V. Anisimov
> Bilkent University
> Department of Industrial Engineering,
> Bilkent 06533 Ankara, Turkey &
> Kiev University, Ukraine
> Tel: 90-312-290 1539, Fax: 90-312-266 4126
> E-mail: [log in to unmask]
> URL: http://www.bilkent.edu.tr/~vlanis
>
> INTERNATIONAL PROGRAM COMMITTEE
>
> Attahiru Alfa, University of Windsor, Canada
> Jesus R. Artalejo, Universidad Complutense de Madrid, Spain
> Khalid Begain, University of Bradford, UK
> Pavel Bocharov, People Friendship University, Russia
> Srinivas R. Chakravarthy, Kettering University, USA
> Alexander Dudin, Belorussian University, Belorussia
> Tony Field, Imperial College, London, UK
> Guenter Haring, University of Vienna, Austria
> Peter Harrison, Imperial College, London, UK
> Ulrich Klehmet, University of Erlangen, Germany
> Demetres Kouvatsos, University of Bradford, UK
> Igor Kovalenko, Institute of Cybernetics, Ukraine
> A. Krishnamoorthy, Cochin University of Science and Technology,India
> Bruno Mueller-Clostermann, Universitaet GH Essen, Germany
> Marcel Neuts, University of Arizona, USA
> Michael Nikulin, University of Victor Segalen, France
> Krzysztof Pawlikowski, University of Canterbury, New Zealand
> Richard Serfozo, Georgia Institute of Technology, USA
> Bruno Sericola, IRISA-INRIA, France
> Frederick T. Sheldon, University of Colorado, USA
> Christoph Strelen, Universitaet Bonn, Germany
> Janos Sztrik, University of Debrecen, Hungary
> Baris Tan, Koc University, Turkey
> Kishor Trivedi, Duke University, USA
> Dietmar Tutsch, Technical University Berlin, Germany
>
> PAPER SUBMISSION TYPES
>
> FULL PAPER (including abstract, conclusions, diagrams, references)
> During review, the submitted full papers can be accepted as a
> regular 5 page paper. If excellent, full papers can be accepted by
> the program committee as an extended (8-page) paper. Each
> submission will be reviewed by at least three members of the
> International Program Committee.
>
> EXTENDED ABSTRACT (at least five pages) Participants may also
> submit a 5 page extended abstract for a regular (5 pages) or short
> (3 pages) paper or poster, which will be reviewed by the
> International Program Committee. All accepted papers will be
> published in the ESM'2001 Conference Proceedings.
>
> SHORT ABSTRACT (at least three pages) Participants may also submit
> a 3 page abstract for a short paper or poster, which will be
> reviewed by the International Program Committee. All accepted
> papers will be published in the ESM'2001 Conference Proceedings.
> ONE PAGE ABSTRACTS ARE NOT ACCEPTED.
>
> Five copies of full papers (5 pages) or extended abstracts
> (3 pages) should be submitted, in printed form or alternatively
> as an e-mail containing an ASCII text, rtf, pdf, LaTex, PostScript
> or uuencoded Word file to:
>
> Philippe Geril
> SCS Europe, University of Ghent
> Coupure Links 653
> B-9000 Ghent, Belgium
> Tel (Office): +32 9 2337790
> Fax: + 32 9 2234941
> T+F Private: +32 59 800 804
> Email: [log in to unmask]
>
> To save time for reviewing process please send electronic versions
> of papers in parallel to
> Vladimir Anisimov
> Email: [log in to unmask]
>
> OUTSTANDING PAPER AWARD The 2001 European Simulation
> Multiconference Committee will select the Outstanding Paper of the
> Conference. The author of this paper will be awarded a free
> registration for an SCS conference.Only papers SUBMITTED AS FULL
> papers will be eligible for the Outstanding Paper Award.
>
> LANGUAGE The official conference language for all papers and
> presentations is English.
>
> REGISTRATION FEES
>
> Registration Fees
> Author SCS/EUROSIM Other
> Member Participants
> Pre-reg before 450 EURO 450 EURO 525 EURO
> April. 30th 2001
>
> Registration after Pre-registration 525 EURO 575 EURO
> April 30th '2000 required
>
> The registration fee includes one copy of the Conference
> Proceedings, coffee and tea during the breaks, all lunches, a
> welcome cocktail and the conference dinner.
>
> IMPORTANT DEADLINES
> January 15, 2001: Submit contributed full-papers (5 to 8 proceedings
> pages) not previously published. These submissions, when accepted
> will be published as regular or extended papers, depending on their
> quality.
>
> January 15, 2001: Submit extended abstracts (5 abstract pages) or
> short papers (3 abstract pages), reports of industrial projects
> and summaries of posters. These submissions, when accepted will
> be published as regular, of up to 5 proceedings page papers.
>
> January 15, 2001: Submit one -to -three page proposals to present
> tutorials, to organise and chair panel sessions, to organise user
> meetings, vendor sessions or to exhibit software
>
> January 15, 2001: Submit abstracts for student and poster session
>
> February 25, 2001: Acceptance Notification
>
> April 30, 2001: Authors provide camera-ready manuscript
>
> June 6-9, 2001: Conference
>
> VENUE: PRAGUE, CZECH REPUBLIC
>
> The conference will be held in the beautiful city of Prague,
> capital of the Czech Republic, which offers its visitors a
> breathtaking historical environment in which to enjoy the ESM'2001.
> The conference site itself will be
> the Masarykova kolej, Thákurova 1,160 41 Prague 6, Czech Republic
>
> --------------------------------------------------------------------------
> REPLY CARD
>
> First Name:
> Surname:
> Occupation and/or Title:
> Affiliation:
> Mailing Address
>
> Zip code:
> City: Country.
> Telephone: Fax:
> E-Mail:
>
> Yes, I intend to attend the ESM'2001:
> [ ] Presenting a paper, by submitting a full paper
> [ ] Presenting a short paper (by submitting an extended abstract)
> [ ] Participating in the industrial program
> [ ] Organizing a vendor session
> [ ] Proposing a panel discussion (please mention names of panellists)
> [ ] Contributing to the exhibition
> [ ] Without presenting a paper
> The provisional title of my paper / exhibited tool is:
>
> With the following highlights:
>
> The paper belongs to the category (please tick only one):
> [ ] Methodology and Tools
> [ ] Simulation in Engineerings
> [ ] Parallel and Distributed Simulation
> [ ] Verification, Validation & Verification
> [ ] Military Simulation
> [ ] Neural Nets and Datamining
> [ ] High Performance Computing
> [ ] Analytical and Stochastic Modelling Techniques
> [ ] Simulation in Biology and Medicine
> [ ] Poster session
> [ ] Student Session
>
> Other colleague(s) interested in the topics of the conference is/are:
> Name:
> Address:
> Name:
> Address:
> If you would like to receive more information about SCS and its
> activities, please tick the following box:
> [ ] YES, I would like to know more about SCS
> [ ] NO, please remove me from your database.
>
> Please send or fax this card immediately to: (fax: +32.9.223.49.41)
> Philippe Geril, Society for Computer Simulation, European SCS Europe,
> University of Ghent, Coupure Links 653, B-9000 Ghent, Belgium
>
> Further Information:
>
> 15th European Simulation Multiconference
> http://hobbes.rug.ac.be/~scs/conf/esm2001/
>
> ASMT'2001 Conference
> http://www.bilkent.edu.tr/~vlanis/ASMT'2001.html
>
> SCS European Office
> http://hobbes.rug.ac.be/~scs
>
> ------------------------------
>
> Date: Fri, 24 Nov 2000 11:23:16 +0100 (MET)
> From: Jim Lindsey <[log in to unmask]>
> To: [log in to unmask]
> Subject: lecturer position in Belgium
> Message-Id: <[log in to unmask]>
>
> A tenure-stream position of lecturer in statistics is available at the
> Mathematics Institute of the University of Liege to begin on 1
> October, 2001. Tenure can be granted after three years.
>
> Teaching duties will include:
> Mathematical statistics: 30hr lectures plus 10hr exercises
> Time series: 30hr lectures plus 10hr exercises
> Stochastic processes: 30hr lectures plus 10hr exercises
>
> A candidate must have a Ph.D. Priority will be given to those with
> proven research record in applied and theoretical statistics.
>
> The deadline for applications has yet to be fixed by the Moniteur Belge.
>
> For addition information, please contact
>
> Marc Roubens: +32-4-366.94.10 or [log in to unmask]
>
> Adelin Albert: +32-4-366.25.91 or [log in to unmask]
>
> Jim Lindsey: +32-4-366.29.64 or [log in to unmask]
>
> at the Interdisciplinary Centre for Statistics of the University of Liege.
>
> ------------------------------
>
> Date: Fri, 24 Nov 2000 12:02:23 -0000
> From: "Abrams, Dr K.R." <[log in to unmask]>
> To: "[log in to unmask]" <[log in to unmask]>
> Subject: TALK: RSS Med Sect Tues 28th Nov 3pm @ RSS London
> Message-Id: <[log in to unmask]>
>
> The next RSS Medical Section meeting will take place NEXT
> Tuesday, 28th November, at 3pm (Tea at 4pm) at the RSS in
> London, when there will be two talks on the use of hierarchical/
> multilevel models in health/medical research.
>
> All are very welcome. Directions to the RSS can be found at
> http://www.rss.org.uk/
>
> PAUL BURTON (University of Leicester)
> Generalised Linear Mixed Models (GLMMs) in genetic epidemiology
>
> This talk will consider the application of WinBUGS-based generalised linear
> mixed models (GLMMs) to a wide range of problems in genetic epidemiology. I
> will describe the structure of the GLMMs and say something about how we fit
> them. I will explain why they are useful to genetic epidemiologists and are
> also of potential use to other bio-statisticians who are faced with family
> data to analyse. Finally, I will consider the thorny problem of adjusting
> the GLMMs for non-random ascertainment of families.
>
> ALASTAIR H LEYLAND (University of Glasgow)
> Multilevel models in Public Health and Health Services Research
>
> The data that are collected for Public Health and Health Services Research
> are frequently hierarchical; for example, through the organisation of health
> services or the clustering of populations. Further levels may exist, for
> example if the data comprise repeated measures or multiple responses. This
> talk illustrates such models using examples concerned with the evaluation of
> hospital performance, epidemiology, measuring inequalities in health and
> disease mapping. Pseudo-likelihood and Markov chain Monte Carlo estimation
> methods are discussed using the MLwiN software.
>
>
>
> Dr Keith R. Abrams
> Reader in Medical Statistics
> Department of Epidemiology & Public Health
> University of Leicester
> 22-28 Princess Road West
> Leicester, U.K.
> LE1 6TP
> Tel +44 (0)116 252 3217
> FAX +44 (0)116 252 3272
> e-mail [log in to unmask]
> WWW http://www.prw.le.ac.uk/
>
> ------------------------------
>
> Date: Fri, 24 Nov 2000 12:45:08 -0000
> From: "Ewan Crawford" <[log in to unmask]>
> To: <[log in to unmask]>
> Subject: ADMIN: Mailbase to JISCmail changeover
> Message-Id: <[log in to unmask]>
>
> ADMIN: Allstat; Mailbase to JISCmail changeover
>
> >From Monday the 27th of November 2000, Allstat, (along with all other free
> lists on Mailbase), will no longer run using Mailbase; it will run using
> JISCmail. Members of Allstat will be automatically forwarded to JISCmail.
>
> For Allstat members two operational features will change;
>
> 1. Allstat E-mail addresses
>
> The Allstat e-mail addresses are changing;
>
> To send to the list you will need to write to
> [log in to unmask]
>
> To contact the list-owner you should write to
> [log in to unmask]
> (you may also write directly to [log in to unmask]),
>
> To send commands (e.g. join, leave, suspend, resume etc.) write a correctly
> formated message to
> [log in to unmask]
>
> 2. Allstat Commands (e.g. join, leave etc)
>
> The commands to join, leave and suspend Allstat should be sent to a new
> address and in some cases have a new syntax.
> More information on this is given in the new versions of the Allstat
> Introduction and FAQ that will be sent in a following e-mail.
>
> The Allstat web pages at
> http://www.stats.gla.ac.uk/allstat
> have already been changed.
>
> As well as what these documents contain some new commands and options will
> be available with JICSmail in future; we shall let you know of these as
> they become available.
>
> Note that to leave allstat you shall need to send the message
> leave allstat
> to
> [log in to unmask]
>
> To suspend your mail (note that this is different from Mailbase), send
> set allstat nomail
> to
> [log in to unmask]
>
> and to resume receiving Allstat, send
> set allstat mail
> to
> [log in to unmask]
>
> Some of you may be curious about this change. What follows is a brief
> explanation of the reasons for the change.
>
> Some time ago the Joint Information Systems Committee (JISC), which
> previously funded Mailbase, awarded the contract for providing the National
> Academic Mailing List Service to the Council for the Central Laboratories of
> the Research Councils (CCLRC) in Oxfordshire, after putting the contract to
> tender. Newcastle University, which created Mailbase and has run it until
> now, was not successful in the tendering process.
>
> As well as changing the provider, it was also decided to change the name of
> the Service and the software that runs it. The name was changed as the
> copyright on the name Mailbase is owned by the Royal Mail and, though the
> Royal Mail had previously allowed it to be used, JISC decided to choose
> another one that could remain constant in future. The software was changed
> from that developed by Newcastle themselves to the commercially available
> LISTSERV software; note that this change would also have occured if
> Newcastle had not lost the contract.
>
> Please send any queries or comments about this to me at
> [log in to unmask]
> or
> [log in to unmask]
> and not to the list. However, I would ask that you check the new Allstat
> Introduction & FAQ and the JISCmail web site - http://www.jiscmail.ac.uk/ -
> before contacting me.
>
> Regards,
>
> Ewan
>
> ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
> Dr Ewan Crawford
> Allstat list owner
> LTSN Maths, Stats & O.R. Centre
> Department of Statistics Phone : +44 (0)141 330 4873
> University of Glasgow Fax : +44 (0)141 330 4814
> ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
> [log in to unmask] http://www.stats.gla.ac.uk/allstat
> ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
>
> ------------------------------
>
> Date: Fri, 24 Nov 2000 15:17:34 +0000
> From: Emilia Vynnycky <[log in to unmask]>
> To: allstat <[log in to unmask]>, ornet <[log in to unmask]>
> Cc: Richard White <[log in to unmask]>
> Subject: new modelling short course
> Message-Id: <[log in to unmask]>
>
> Dear list members
>
> Please circulate the advert below about this new (and exciting!) course on infectious disease modelling to anyone who may be interested.
>
> Thanks in advance!
>
> Emilia Vynnycky
> Lecturer in Infectious Disease Modelling
> London School of Hygiene & Tropical Medicine
> UK
>
> 2 week intensive course on:
>
> "INTRODUCTION TO INFECTIOUS DISEASE MODELLING AND ITS APPLICATIONS"
>
> at the London School of Hygiene & Tropical Medicine
>
> 9-20th July 2001
>
> Summary:
> Mathematical modelling is increasingly being applied to interpret and predict the dynamics and control of infectious diseases. Applications include predicting the impact of vaccination strategies against infections such as measles, rubella and polio and determining optimal control strategies against HIV and onchocerciasis.
>
> This two week intensive course is intended to introduce professionals working on infectious diseases to this exciting and expanding area. The emphasis will be on developing a conceptual understanding of the basic methods and on their practical application, rather than the manipulation of mathematical equations.
>
> Who should attend:
> The course is designed for individuals interested in expanding their knowledge of the techniques for analysing and interpreting epidemiological data on infectious diseases and for predicting the impact of control programmes, including medical and health professionals, policy makers, veterinary scientists, medical statisticians and infectious disease researchers.
>
> Specialist mathematical training is not a prerequisite. However, individuals with degrees in mathematical disciplines working on some aspect of infectious disease dynamics and/ or control, who wish to learn about the potential of infectious disease modelling will also benefit.
>
> For copies of the leaflet and application form, please contact:
> Registry
> London School of Hygiene & Tropical Medicine
> 50 Bedford Square
> London,
> WC1B 3DP
> UK
> email: [log in to unmask]
>
> For details about the course content, please contact one of the course organizers:
> Emilia Vynnycky or Richard White
> e-mail: [log in to unmask] or [log in to unmask]
>
> Details of the course are posted on:
>
> http://www.lshtm.ac.uk/itd/units/ideu/ModellingShortCourse.htm
>
> or visit http://www.lshtm.ac.uk
>
> ------------------------------
>
> Date: Fri, 24 Nov 2000 15:34:02 -0000
> From: "Sheehan, Dr N.A." <[log in to unmask]>
> To: "[log in to unmask]" <[log in to unmask]>
> Subject: RSS East Midlands - November Meeting cancelled
> Message-Id: <[log in to unmask]>
>
> Unfortunately, due to unpredicatability of public
> transport to and from the Midlands at the moment,
> next week's seminar at the University of
> Nottingham has had to be postponed until the New
> Year.
>
> Please note that this is the talk on
> "Estimating mixtures of regressions"
> due to be held on Thursday, November 30,
> at 4.30pm, Room C12 of the Mathematics
> and Physics Building at Nottingham University
>
> The new arrangements will be available on our
> website as soon as possible.
> http://www.prw.le.ac.uk/epidemio/personal/nas11/rsscurrent.html
>
> I apologise for any inconvenience this may cause.
>
> Nuala A. Sheehan,
> Department of Epidemiology and Public Health,
> University of Leicester,
> 22-28 Princess Road West,
> Leicester LE1 6TP, UK
>
> Tel: +44 (0)116 2525456
> Fax: +44 (0)116 2523272
> Email: [log in to unmask]
>
> ------------------------------
>
> Date: Fri, 24 Nov 2000 15:50:01 GMT
> From: Charles Taylor <[log in to unmask]>
> To: [log in to unmask]
> Cc: [log in to unmask]
> Subject: SIAP meeting: 6/12/00
> Message-Id: <[log in to unmask]>
>
> SIAP meeting : Industrial Image Analysis
>
> Wednesday, 6th December 2000 2-5pm
>
> RSS, 12 Errol Street, London EC1Y 8LX
>
> ______________________________________________________________________
>
> TALK 1: Some problems in the study of magnetic materials
>
> D. M. Titterington (University of Glasgow)
>
> Abstract: The talk will cover a few aspects of the behaviour of
> thin-film magnetic materials under the influence of an external field.
> The materials themselves are used in such applications as modern
> information storage devices and in recording heads in hard disk drives.
> A short introduction to the elements of the underlying physics will be
> attempted, followed by descriptions of stochastic models for dynamic
> magnetisation reversal and of an empirical application of simultaneous
> autoregression models to analyse images of so-called magnetisation
> ripple. The work is the consequence of collaboration with colleagues in
> statistics and physics.
>
> ----------------------------
>
> TALK 2: Image Analysis within Unilever Research: Quantifying
> Product Microstructure
>
> Geert M.P. van Kempen (Unilever Research)
>
> Abstract: It is widely believed that the microstructure of the
> composites typical of Unilever products plays a key role in the
> manifestation of the physical observables and behaviour of the
> materials and ultimately the consumer experience with the product. This
> belief has lead to a need for superior microstructural understanding in
> Unilever?s research activities, with the expectation that this will
> lead to superior product innovation and design. This presentation will
> give an overview of our efforts to quantify product microstructures and
> to discriminate between microstructures of products classes that differ
> on the basis of processing, ingredients or bulk physical properties.
> These efforts can be divided in three parts: the translation of
> microstructural attributes in parameters that can be measured by image
> analysis, classification of the microstructures on the basis of the
> measured parameters, and the identification and quantification of the
> found differences. In the first part of the presentation, the detection
> of minute differences in the microstructure of milk gels will be used
> to illustrate the concepts of the microstructure quantification toolbox
> we are currently developing. In the second part of the presentation,
> the focus will be on the development of advanced image analysis
> procedures to measure microstructure parameters. The measurement of the
> anisotropy and pore-sizes of monoglyceride gels demonstrate multi-scale
> image analysis. Both the monitoring of the dynamics of phase separation
> as well as the measurement of the gas cell size distribution during the
> proofing of dough will illustrate our efforts in time-resolved image
> analysis. Finally, the segmentation of the various phases inside a
> detergent powder particle shows the potential of multi-spectral
> analysis for microstructure quantification. In this particular case, we
> have developed a combined classifier, based on the EM algorithm, that
> uses information from both the spectral as well as the spatial domain
> to obtain improved segmentation results.
>
> The image analysis developments discussed in this presentation are
> developed in close collaboration with the Pattern Recognition Group of
> the Delft University of Technology.
>
> ----------------------------
>
> TALK 3: Industrial Image Analysis: On the interaction between
> research and application
>
> Bjarne Kjaer Ersboell (Technical University of Denmark)
>
>
> Abstract: An element of research is of paramount importance for an
> industrial image analysis project to be interesting for a university
> department. The Section for Image Analysis has been involved in
> numerous industrial image analysis projects during the last twenty
> years. All are characterised by the research being application driven
> rather than method driven. In the process of solving the problem new
> theoretical aspects which need to be solved inevitably turn up. We find
> this interaction between theory and practice extremely inspiring. In
> the talk a small representative selection of industrial image analysis
> projects will be shown with special emphasis on the research
> performed. Finally, we will focus on a project on sorting of
> wood-slabs using image analysis. Here a combination of traditional
> statistical techniques together with some novel theory on feature
> selection was necessary in order to solve the problem.
>
> ------------------------------
>
> Date: Fri, 24 Nov 2000 16:58:14 +0100
> From: [log in to unmask]
> To: [log in to unmask]
> Subject: repeatability and reproducibility
> Message-Id: <[log in to unmask]>
>
> Dear allstatters,
>
> We are often confronted with the determination of the precision of a diagnostic
> test method (e.g. a test to determine wether or not a patient has some kind of
> disease). For test methods where the outcome is quantitative the ISO 5725
> "Precision of a test method - Determination of repeatability and reproducibility
> for a standard test method by inter-laboratory tests" can be applied, which
> clearly shows how to calculate a measure r for repeatability (which is related
> to the within-laboratory variance) and a measure R for reproducibility (which is
> related to the within and between laboratory variance).
>
> However, in many cases we have to deal with tests that have a binary outcome for
> which we have to determine repeatability and reproducibility. For the moment we
> just tabulate the values of each center. Does someone knows how you can define
> these characteristics for qualitative tests?
>
> Thanks a lot,
>
> Annelies De Brauwer
> Innogenetics
> Belgium
>
> ------------------------------
>
> Date: Fri, 24 Nov 2000 15:39:51 GMT
> From: "eric grist" <[log in to unmask]>
> To: [log in to unmask]
> Subject: QUERY: 2 bootstrap questions
> Message-Id: <[log in to unmask]>
>
> I have two questions on applying the bootstrap. Neither of these appear to be
> covered in Efron and Tibshirani's excellent introductory book (1993) 'an introduction
> to the bootstrap'.
>
> Suppose the original sample S contains N elements and comes from a population
> P.
>
> (1) Is there a minimum value for N for which bootstrap resampling (in other
> words, construction of resamples of size N by randomly sampling from S) is either
> NOT valid or not likely to be a good method for estimating the standard error
> or calculating a percentile-based confidence interval of a given statistic of
> interest for P?
>
> (2) If resamples of size M are constructed from S WHERE M IS STRICTLY GREATER
> THAN N, then: (a) as M increases, the bootstrap resamples (of size M) generated
> from S (of size N) become 'less representative' of the original population P
> and thus any estimate of the standard error or a confidence interval calculated
> for a chosen statistic of P is prone to increasing bias as M increases, (b)
> if the statistic of interest is the mean Mu of P, then the distribution of the
> 'resample mean' as calculated from the bootstrap resamples generated from S
> tends towards a NORMAL distribution centred on Mu.
>
> If there are any references which cover these points I would appreciate hearing
> of them.
>
> Many thanks,
>
> Eric Grist
>
> -------------------------------------------------------------
> This email has been sent from Australia's Education
> Internet gateway: http://www.australia.edu
> Sign-up for your free email today
> ------------------- ------- ---------------------------------
>
> ------------------------------
>
> Date: Fri, 24 Nov 2000 16:14:10 +0000
> From: Janet Drewery <[log in to unmask]>
> To: allstat <[log in to unmask]>, seminars <[log in to unmask]>,
> Subject: Biostatistics@Keele Reminder
> Message-Id: <[log in to unmask]>
>
> CENTRE FOR MEDICAL STATISTICS
>
> SEMINAR SERIES on BIOSTATISTICS 2000/2001
>
> NO 1: Wednesday, November 29th, 2000, at 2:30 pm
>
> Can We Define and Detect Gene-Gene, Gene-Environment and
> Gene-Treatment Interactions?
>
> by
>
> Professor David Clayton
>
> (Wellcome Trust Principle Research Fellow
> Department of Medical Genetics
> University of Cambridge)
>
> There is a widespread assumption that recent advances in mapping
> the human genome will have profound implications for epidemiology
> and for therapeutic research, and that this will largely be achieved
> through the identification of "interaction". In epidemiology, it is a
> rare grant application which does not highlight the possibilities for
> the study of "gene-environment interaction". Yet such claims rarely
> define the notion with any precision, or discuss the manner in which
> statistical interaction relates to interaction in the mechanistic sense
> understood by biologists.
>
> This paper will review the various ways in which interaction arises in
> statistical analysis of genetic epidemiological studies, and discusses
> the implications for study design.
>
> All welcome!!
>
> Venue:
> The Art Gallery
> Chancellor's Building
> Keele University
>
> http://www.keele.ac.uk
> http://www.keele.ac.uk/depts/ma/seminars/medstats.html
> http://www.keele.ac.uk/university/campus/maps/
>
> ____________________________
>
> Janet Drewery
> Secretary
> Centre for Medical Statistics
> Keele University
> Staffordshire ST5 5BG
> England
>
> Email: [log in to unmask]
>
> Tel: (01782) 583269
> Fax: (01782) 583269/584268
> ______________________________
>
> ------------------------------
>
> Date: Fri, 24 Nov 2000 15:55:11 GMT
> From: "eric grist" <[log in to unmask]>
> To: [log in to unmask]
> Subject: QUERY : 2 BOOTSTRAP Questions
> Message-Id: <[log in to unmask]>
>
> I have two questions on applying the bootstrap. Neither of these appear to be
> covered in Efron and Tibshirani's excellent introductory book (1993) 'an introduction
> to the bootstrap'.
>
> Suppose the original sample S contains N elements and comes from a population
> P.
>
> (1) Is there a minimum value for N for which bootstrap resampling (in other
> words, construction of resamples of size N by randomly sampling from S) is either
> NOT valid or not likely to be a good method for estimating the standard error
> or calculating a percentile-based confidence interval of a given statistic of
> interest for P?
>
> (2) If resamples of size M are constructed from S WHERE M IS STRICTLY GREATER
> THAN N, then:
> (a) as M increases, the bootstrap resamples (of size M) generated from S (of
> size N) become 'less representative' of the original population P and thus any
> estimate of the standard error or a confidence interval calculated for a chosen
> statistic of P is
> prone to increasing bias as M increases,
> (b) if the statistic of interest is the mean Mu of P, then the distribution
> of the 'resample mean' as calculated from the bootstrap resamples generated
> from S tends towards a NORMAL distribution centred on Mu.
>
> If there are any references which cover these points I would appreciate hearing
> of them.
>
> Many thanks,
>
> Eric Grist
>
> -------------------------------------------------------------
> This email has been sent from Australia's Education
> Internet gateway: http://www.australia.edu
> Sign-up for your free email today
> ------------------- ------- ---------------------------------
>
> ------------------------------
>
> Date: Fri, 24 Nov 2000 16:11:56 -0000
> From: "Ewan Crawford" <[log in to unmask]>
> To: <[log in to unmask]>
> Subject: ADMIN: Allstat on JISCmail Introduction
> Message-Id: <[log in to unmask]>
>
> ----------------------------------------------------------------------------
> Introduction to Allstat
> ----------------------------------------------------------------------------
>
> Allstat is a UK-based worldwide e-mail broadcast system for the statistical
> community. This list is operated by the LTSN Maths, Statistics & OR Network,
> and maintained currently by Ewan Crawford in Glasgow. It is now housed at
> the CCLRC's (Council for the Central Laboratory of the Research Councils)
> Rutherford Appleton Laboratory in Didcot, Oxfordshire and is funded by the
> Joint Information Systems Committee (JISC) of the Higher Education Funding
> Councils for England, Scotland and Wales. Previously, it was housed in
> Newcastle University's Mailbase system.
>
> Allstat is intended to provide a fast and simple way of sending information
> to a wide body of statisticians. The list was originally set up by David
> Kerridge in 1988, it was then taken on by Stuart Young in 1991, then Matt
> Whiley in March 1998, John D McClure in December 1999, and most recently by
> Ewan Crawford (in November 2000). Allstat currently has over 2600 list
> members.
>
> While, broadly speaking, any messages relevant to statistics are welcome,
> you are asked to observe the list guidelines outlined in this Introduction.
> Very briefly, the key points to remember are:
> - be sure Allstat is an appropriate forum for your message (there are
> many statistics lists in existence, covering various areas)
> - use meaningful subject lines, with keywords (e.g. CONFERENCE, JOB)
> - send plain text only (no PostScript, Word or encoded files)
> - send text in the body of your message; no attachments
> - no commercial advertising (however job notices, conference
> announcements, etc are permitted)
> - if seeking a reply, include your address in the body of your message
> (or in a signature file)
> - if replying, reply to the sender and not to the list
>
> All of these points are explained fully later, and you should read this
> Introduction thoroughly. Also available is a list of frequently-asked
> questions (FAQ) about list administration, which you may find useful if
> you have a technical query about how the list operates. Please make use
> of the Introduction and the FAQ list to help reduce the list owner's
> administrative work. Your assistance in this is appreciated.
>
> An on-line version of this Introduction file can be accessed through
> Allstat's Web site, at
> http://www.stats.gla.ac.uk/allstat/
> If you view this version, you will find links to many of the items
> mentioned in the text, as many resources are directly available on-line.
>
> List Addresses
> ----------------------------------------------------------------------------
>
> There are four e-mail addresses to note:
>
> (i) [log in to unmask]
> This address automatically broadcasts to the entire list. Only
> members of the list are permitted to use this address.
>
> (ii) [log in to unmask]
> This should be used when sending commands, e.g. leave, join (see later)
>
> (iii) [log in to unmask]
> Messages sent here will go to the list owner. Any administrative
> questions about Allstat should be sent here, although please note
> that, as well as the Allstat FAQ list, extensive JISCmail
> documentation is available to explain the facilities offered to
> users.
>
> (iv) [log in to unmask]
> This address is that of the JISCmail team. Send any comments or
> queries about JISCmail here.
>
> Please note the differences between these addresses, particularly (i) and
> (ii). Commands should NOT be sent to [log in to unmask] as this
> address is ONLY for broadcasts.
>
> Some useful commands
> ----------------------------------------------------------------------------
>
> Note: If your mailer automatically appends a signature file to any messages
> you send out, you may find that the JISCmail software will attempt to
> interpret your signature as a command. To avoid this, insert two hyphens
> --
> on a line by itself, after any other commands you type. All commands
> should be put in the main body of your message, and not in the subject
> field.
>
> Remember that all commands should be addressed to [log in to unmask]
>
> To join Allstat, send a message to
> [log in to unmask]
> containing the single line
> join allstat your name
> e.g. join allstat Ewan W. Crawford
>
> If you have already joined the list, and think your name may have been
> incorrectly registered, simply resend the 'join' command with the corrected
> form of your name. To check your registration, see the 'review' command
> below.
>
> Note that you must supply at least two words as a name, so for example
> E.W.Crawford would be rejected (because there are no spaces and it is
> interpreted as a single word), but E.W. Crawford or E. W. Crawford are fine.
>
> You may wish to receive Allstat in digest form. This allows you to receive
> messages from the list as a single large message. This digest will be sent
> every night, or when more than 20 messages have been sent to Allstat.
>
> To receive Allstat messages as a digest, send a message to
> [log in to unmask]
> containing the single line
> set allstat digest
>
> To change back to receiving messages normally send a message to the same
> address containing the single line
> set allstat nodigest
>
> To leave Allstat, send a message to
> [log in to unmask]
> containing the single line
> leave allstat
>
> To obtain by e-mail an alphabetical listing of all those on Allstat,
> together with their e-mail addresses, send a message to
> [log in to unmask]
> with the command
> review allstat
>
> It is a good idea to suspend your mail if you are going to be away for a
> period of time, as this can prevent your mailbox filling up while you are
> absent. To do this, send a message to
> [log in to unmask]
> with the command
> set allstat nomail
>
> To reverse this on your return, the command is 'set allstat mail'.
> You can use the archives to catch up on any messages you missed.
>
> Allstat also acts as an e-mail directory of statisticians. If you wish to
> appear in this directory for contact purposes, but do not wish to receive
> list mail directly, join the list in the usual way and then suspend your
> mail by following the instructions above. Note that you can still read
> the archived broadcasts, if you wish.
>
> To find out all the JISCmail lists your e-mail address is registered on,
> send a message to
> [log in to unmask]
> with the command
> query *
>
> To obtain by e-mail a list of available documentation about JISCmail, send a
> message to
> [log in to unmask]
> with the command
> info
>
> When you have found the document you require, use the 'get
> FILENAME.FILETYPE'
> command to have it posted to you. For example, to receive the Common User
> Commands reference card by e-mail, send a message to
> [log in to unmask]
> with the command
> get JISCUSER.REFCARD
>
> List Archives
> ----------------------------------------------------------------------------
>
> Messages to Allstat are archived. Each month's messages are grouped
> together, and retained for a year. To get a list by e-mail of all the
> files available (archived messages and other files), send a message to
> [log in to unmask]
> with the command
> index allstat
>
> When you have found the month's archive you require, use the 'get
> allstat.LOGYYMM' command to have it posted to you. For example, to receive
> the October 2000 archive by e-mail, send a message to
> [log in to unmask]
> with the command
> get allstat.LOG0010
>
> To retrieve a file use the 'get allstat\FILENAME.FILETYPE' command. For
> example, to request the Allstat FAQ by e-mail, the command is
> get allstat\faq.txt
>
> Note that as an alternative to e-mail, all the documents mentioned so far,
> including the Allstat message archive, can be accessed from the Allstat
> Web site. The hypermail Web archive allows viewing of individual messages,
> and you can sort by date, subject, author and thread. You can also search
> the archives on the Web.
>
> The e-mail archives are updated every time a message is sent out to the
> list, and the Web archive is updated every day.
>
> Finding the correct forum - other statistics lists
> ----------------------------------------------------------------------------
>
> If you have a message you wish to send, and you are not sure if Allstat is
> appropriate, you are advised to examine the various outlets available to
> you. There are mailing lists covering many different areas of statistics,
> and there are obvious benefits to yourself, and to the recipients of your
> message, if you ensure it is posted to the correct forum. This is
> particularly important if your message is of a consultancy nature, or is
> likely to provoke discussion, and might therefore be more suited to a list
> other than Allstat. Also, if you have a query about a particular piece of
> software, you will find that most of the major packages have their own
> dedicated lists, which you should use.
>
> There is a document which details many of the statistics-related lists
> worldwide, including instructions on how to join them. This "list of lists"
> file is maintained by the owner of the Minitab list on JISCmail, Mike Fuller
> ([log in to unmask]). This file is available on the web at
>
> http://www.ukc.ac.uk/php/mff/netres/statlist.html
>
> The Allstat website also includes a number of links to other statistical
> mailing lists.
>
> Format for messages
> ----------------------------------------------------------------------------
>
> Please send messages in plain text format only. If documents are available
> in other formats (e.g. Word, PostScript, etc) then by all means indicate
> this in your message and give instructions on how to obtain such files (e.g.
> on request by personal e-mail, or from a Web or ftp site). Since not all
> users are able to handle these alternative formats, please limit your
> Allstat broadcasts to plain text, and ensure that the text is carried in
> the main body of your message; do not send attachments to the list.
>
> Some mailers have the facility to send encoded messages, which are
> unreadable until decoded. Please take care that you do not unwittingly
> select this option.
>
> If you are looking for replies to a message you are sending, you should
> ensure that your own e-mail address is listed somewhere in the body of the
> text. Some mailers can have difficulties in handling the automatic header.
>
> When sending seminar notices to the list, it would be most effective to do
> this once at the beginning of term. It is generally not very helpful to
> send last-minute reminders about seminars to a list which is as
> geographically spread as Allstat.
>
> Subject lines
> ----------------------------------------------------------------------------
>
> Members are asked to use meaningful subject lines when sending out
> broadcasts. The benefits are obvious, particularly when browsing through
> the archives for a specific message. In particular, posters are requested
> to use clear keywords in subject lines, to give an indication of content.
> The following convention has been adopted:
> JOB - jobs or studentships
> SEMINAR - seminar announcements
> CONFERENCE - conference announcements
> COURSE - taught course announcements
> WORKSHOP - workshop announcements
> ANNOUNCE - other announcements
> QUERY - for queries
> S/W ADVERT - for a software advert *
> BOOK ADVERT - for a book advert *
> ADMIN - administration messages (from the list owner)
>
> A sample subject line may read
> JOB: temporary lectureship at Glasgow University, UK
>
> Where appropriate, a geographical location should be included in the subject
> line.
>
> * The ADVERT categories are only to be used by the list owner, in forwarding
> messages from advertisers. See below for the guidelines on advertising on
> the list.
>
> Virus alerts
> ----------------------------------------------------------------------------
>
> Occasionally, rogue virus alerts crop up, warning of a virus which is
> spread simply by reading an e-mail. These are hoaxes, as you cannot catch
> a computer virus from a plain text e-mail message: another good reason for
> restricting broadcasts to this format. If you are worried about a virus
> alert, either consult a Virus Information Web site (e.g.
> http://www.ncsa.com/services/consortia/anti-virus/alerthoax.html), or
> contact the list owner, rather than alarming the list, perhaps
> unnecessarily.
>
> Commercial Advertising
> ----------------------------------------------------------------------------
>
> Commercial advertising is against the JANET Acceptable Use Policy. However,
> publicising items of potential interest to list members, such as training
> courses, software etc, can be to the benefit of the list. If the
> "publicity" comes from the person likely to make money out of it, then that
> falls into a grey area. If you have a message which you feel may come under
> this category, then you are advised to first send the message to the list
> owner ([log in to unmask]). If the message is suitable, the
> list owner will forward it to the list on your behalf. In general,
> "routine" advertising will not be approved; new releases or limited special
> offers are more likely to be accepted, and shorter messages are recommended
> (with pointers to sites for further information, if available).
>
> Job adverts and conference notices are perfectly acceptable, and can be
> posted directly to the list.
>
> Replying to Allstat broadcasts
> ----------------------------------------------------------------------------
>
> The list is set so that replies to messages are directed to the sender, and
> not to the list. This is deliberate. Generally, if responding to a
> message, it is best to reply by personal e-mail, and not to the list. If
> appropriate, a summary of responses can be sent to the list by the original
> poster in due course. Allstat is intended to be an information provider,
> rather than a discussion list.
>
> If your mailer does not allow you to see the address of the original poster,
> and they have not provided a reply address in the body of the message (e.g.
> in a signature file), then please note that the archives will contain the
> address, and you can obtain it there, if you wish to respond. Please do
> not be tempted to simply reply to the list.
>
> Some mailers can be set so that responses, as well as going to the sender,
> are also copied to the list. If your mailer is one of these, please ensure
> that this option is not enabled, and that your response goes only to the
> sender.
>
> Forwarding messages
> ----------------------------------------------------------------------------
>
> Broadly speaking, it is a breach of copyright to forward list messages
> without the author's permission. Often however, you may be sending an
> announcement to the list (e.g. conference publicity) which you would be
> happy for list members to forward to other interested parties. If this is
> the case, then it is recommended that you include a short sentence to this
> effect, either in the body of your message, or in your signature.
>
> Problematic Addresses
> ----------------------------------------------------------------------------
>
> With a list the size of Allstat, it is inevitable that some e-mail addresses
> on the list will become unreachable, for whatever reason (see the note below
> on Changing your address). Incidentally, all error messages come to the
> list owner, and are invisible to the list. When repeated error messages come
> in regarding an account, action has to be taken to remove that account from
> the list, otherwise the list owner's mailbox would quickly overflow. In
> such circumstances, it is not always possible to get in touch with the
> person concerned, to point out what has happened.
>
> If you should find yourself in the position of suddenly being removed from
> the list without warning, then it would be for the reason outlined above.
> If the problem is temporary, you are welcome to rejoin the list when the
> problem is resolved: it is recommended that you first discuss it with
> your system manager or service provider. Remember that the archives are
> readily accessible, for retrieving any messages you may have missed while
> unsubscribed.
>
> Also note that too many error messages are received for it to be practical
> for the list owner to retain them, so please do not ask for copies.
>
> Changing your address
> ----------------------------------------------------------------------------
>
> If your e-mail address should change, please ensure your Allstat entry is
> kept up-to-date. You can do this yourself, by leaving Allstat under your
> old address, and re-joining under the new one. The procedure for doing this
> is given earlier in this document. Note that this applies to any change,
> even something as apparently minor as a shortening of 'glasgow' to 'gla',
> for example.
>
> When you send commands, such as 'leave' or 'suspend mail', to JISCmail, it
> uses your e-mail address to recognise you. If your address (in the 'From'
> field of your message) does not match up with your list registration on
> JISCmail, then the software will not recognise you, and will inform you that
> you are not registered on the list, and so you will be unable to unsubscribe
> yourself or suspend your mail. This is why it is important to keep your
> registration up-to-date. If you should find yourself in this situation, you
> can contact the list owner ([log in to unmask]) to correct
> matters for you.
>
> If you are incorrectly registered, and you attempt to send a message to the
> list, then you will be prevented from doing so, as only recognised members
> are permitted to send Allstat broadcasts. This is another reason to make
> sure your registration is kept up-to-date. The command 'listme' is a useful
> way to check your registration. Please see the FAQ (Frequently-Asked
> Questions) List for more detailed information about this.
>
> Keeping the list up-to-date helps with its smooth running, enables the
> JISCmail program to recognise you should you interact with it, and helps
> others who may wish to contact you.
>
> 1996 UK Directory of Academic Statisticians
> ----------------------------------------------------------------------------
>
> The Allstat archives also contain the 1996 version of the UK Directory
> of Academic Statisticians, which gives names and contact details, listed
> alphabetically by institution.
>
> For information on how to retrieve this e-mail archive of the 1996
> Directory, send a message to
> [log in to unmask]
> containing the command
> get allstat\directory_readme.txt
>
> Note that some entries in this older version may now be out of date
> (please do not contact me regarding updates). The 1999 version of the
> Directory is available on the Web at
> http://www.swan.ac.uk/statistics/das/
> Users with Web access are encouraged to use this version - the e-mail
> archive is intended mainly for those without Web access, or with a
> slow connection.
>
> Author : Dr Stuart G. Young
> Updated : 14th November 2000 by John D. McClure
> Any comments/queries to : [log in to unmask]
> Allstat Web site : http://www.stats.gla.ac.uk/allstat/
>
> ------------------------------
>
> Date: Fri, 24 Nov 2000 17:28:27 -0000
> From: "Darren Greenwood" <[log in to unmask]>
> To: [log in to unmask]
> Cc: [log in to unmask]
> Subject: JOB: Chair of Statistical Epidemiology at Leeds University, UK
> Message-Id: <[log in to unmask]>
>
> THE UNIVERSITY OF LEEDS
>
> SCHOOL OF MEDICINE
>
> ACADEMIC UNIT OF EPIDEMIOLOGY & HEALTH SERVICES RESEARCH
>
> CHAIR OF STATISTICAL EPIDEMIOLOGY
>
> Applications are invited for the newly established post of Chair of Statistical
> Epidemiology based in the Academic Unit of Epidemiology and Health Services
> Research within the School of Medicine at the University of Leeds. The post
> is available immediately. Applicants should possess a higher degree in medical
> statistics or a related subject (eg. epidemiology), have had appropriate
> training in statistics, and have a proven and significant research and
> publication record together with demonstrated administrative and teaching
> skills.
>
> The salary will be within the non-clinical professorial range.
>
> Informal enquiries about the post may be made to Professor C P Wild (0113 233
> 6601) or Professor D Forman (0113 392 4309).
>
> Further particulars and an application form may be obtained from Ann E Milner,
> Administrative Officer, Human Resources, The University of Leeds, Leeds, LS2
> 9JT, tel: 0113 233 5775, fax: 0113 233 5779; e-mail: [log in to unmask]
> quoting job reference number 097-302-002-001.
>
> The closing date for receipt of applications is 5 January 2001.
>
> Darren Greenwood
> Lecturer in Medical Statistics
> Academic Unit of Epidemiology & HSR
> University of Leeds
> 71-75 Clarendon Road
> Leeds. LS2 9PL
>
> email: [log in to unmask]
> tel: 0113 233 4831
> fax: 0113 233 3952
>
> ------------------------------
>
> Date: Fri, 24 Nov 2000 17:36:20 -0600
> From: Roberto Santana <[log in to unmask]>
> To: [log in to unmask]
> Subject: ISAS 2001, Last Call for Papers
> Message-Id: <[log in to unmask]>
>
> --- apologies for cross posting ----
>
> LAST CALL FOR PAPERS
>
> ISAS 2001
> International Symposium on Adaptive Systems
>
> "Evolutionary Computation and Probabilistic
> Graphical Models"
>
> Hotel Palco and Havana Convention Center, Cuba
> March 19-23, 2001
>
> ( http://isas2001.tripod.com/symp )
> Deadline: December 8, 2000
> -------------------------------------------------------
> The following information has been added to the web page.
>
> 1) First tentative schedule
>
> 2) Important notes for United States Citizens and Residents
>
> 3) Information on special rates in the conference hotels
>
> ------------------------------------------------------
>
> ISAS 2001 will be held in Havana in the period 19-23 March 2001 in
> the context of the International Conference CIMAF
> 2001.
>
> The major themes of the symposium are evolutionary
> computation or hybrid evolutionary approaches,
> and bayesian learning or learning in graphical models.
>
> ----------------------------------
> - Scientific Programme
>
> Our main purpose is to bring together researchers,
> coming from different communities, who share the
> common feature of being involved in using the
> dependence structure of a complex statistical model in
>
> some aspect of evolutionary computation and other
> modern heuristic or soft-computing techniques.
> Cross-fertilization between graphical model research
> and different soft-computing approaches, such as
> genetic algorithms and other evolutionary algorithms,
> as well as neural network learning, reinforcement
> learning, decision tree learning, etc, will be
> strongly encouraged by the conference. However, the
> topics
> of interest to this conference include but are not
> limited to the following:
>
> - Genetic algorithms
> - Learning Bayesian Models from data.
> - Genetic programming
> - Mixture of Models.
> - Classifier systems, evolutionary learning.
> - Dynamic Bayesian Networks.
> - Evolutionary optimization.
> - Gaussian Graphical Models.
> - Constraint, global and multiobjective optimization
> - Model selection.
> - Evolutionary strategies
> - Monte Carlo methods.
> - Graphical Models and Evolutionary Computation.
> - Junction tree algorithms.
> - Graphical Models and Neural Networks.
> - Simulation in Graphical Models.
> - Reinforcement learning.
> - Theoretical Foundations of G. Models
> - Bayesian and Evolutionary Data Mining.
> - Stochastic algorithms
> - Other soft-computing heuristics.
> - Models with latent variables
> - Stochastic Dynamical Systems.
> - G. Models in Game Theory
> - Theoretical Foundations of EC
>
> ------------------------------------------------------
>
> - Symposium chair
> Dr. Alberto Ochoa Rodríguez, Cuba
>
> - Technical Chairs
> Heinz Muehlenbein, Germany
> Tom English, USA
> Pedro Larrañaga, Spain
>
> -------------------------------------------
> - Publication of papers
>
> Conference proceedings will be published and be
> available for the delegates at the conference in
> printed form. In addition the authors of the best
> submissions will be invited to expand and refine
> their papers for possible publication in one leading
> international journal.
>
> The working language is English.
>
> -------------------------------------
> - Important dates:
>
> December 8, 2000 -- > Deadline for submission of
> papers (<=8 pages)
> January 19, 2001 -- > Notification of acceptance
> Febraury 1, 2001 --> Deadline for camera-ready
> copies of accepted papers and registration of
> at least one author
> March 19-23, 2001 --> Conference
>
> ---------------------------------------------
> For further information please contact:
>
> ISAS 2001 URL:
> http://isas2001.tripod.com/symp
> http://www.members.tripod.com/~isas2001/symp/
>
> Dr. Alberto Ochoa Rodríguez
> Institute of Cybernetics, Mathematics and Physics
> (ICIMAF).
> Center of Mathematics and Theoretical Physics.
> Calle 15 No. 551 e/ C y D.
> CP. 10400. La Habana. Cuba.
> Fax: 537-333373
> Phone: 537-327764
> [log in to unmask]
> [log in to unmask]
>
> ------------------------------
|
