On behalf of Michael Greenacre and Albert Satorra I forward
the following course announcement to the list:
===========================================================
6th Applied Statistics Week
Short Courses
STATISTICS IN SOCIETY
Barcelona, 26-30 June 2000
This information, as well as the registration forms, are available at:
http://www.upf.es/idec/estiu/applied.htm
AIMS
The sixth APPLIED STATISTICS WEEK is being organized by
the Pompeu Fabra University (UPF) from 26 to 30 June 2000,
in Barcelona.
The APPLIED STATISTICS WEEK aims to provide a set of intensive
short courses on a particular statistical theme of an
applied nature. The courses are presented by acknowledged
leading researchers of international stature, who are also known
to have excellent teaching skills.
Past themes of the APPLIED STATISTICS WEEK have been:
"Statistics in the Health Sciences" (1995), "Statistics in Classifi-
cation and Pattern Recognition" (1996), "Design and Analysis of Survey
Data" (1997), "Statistics in Environmental Science" (1998) and
"Statistics in Marketing Research" (1999). As this is the Millennium
year, we have decided to enlarge the scope of the courses to
include three important issues of today's society: education, law
and politics. This year's theme is "Statistics in Society".
The first course, presented by Harvey Goldstein of the Institute
of Education, Universiy of London, deals with statistical information
in education in the context of two important problems: the impact of
class size on pupil achievement, and the comparison of schools'
performance. The second course, by David Kaye of Arizona
State University's Collge of Law, aimed at the legal community,
explains the use of probability and statistics in the process of law and
litigation. The third course, by Nick Moon of the research company
NOP in London, is a comprehensive course on public opinion polling
in social and political surveys.
After attending these courses, participants will have an insight into
the important role played by statistics in assisting with problem-solving
and decision-making in these three crucial areas of our society.
We feel that UPF is uniquely placed to foster such intensive courses
of high quality in Spain and, indeed, in Europe as a whole. The university
and the city of Barcelona enjoy an optimal location for gathering scholars
from different parts of Spain and Europe, a city known for its strong
work and innovation ethic as well as its richness of leisure and cultural
activities. The courses are concentrated into one week to facilitate the
enrolment of working professionals and the academic community. We
also promote a lively interaction between participants and instructors
that assists in achieving the goal of improving the application of
statistical concepts and methods to problems in our society.
TARGET AUDIENCE
These courses are aimed at a general audience interested in the themes
to be discussed in education, law and political and social surveys. No
previous statistical knowledge will be assumed. The course on education
is aimed at educationalists, teachers, policy-makers, and educational
researchers. The course on the law is aimed at the legal community
in general, lawyers, advocates, judges and law academics. The course
on opinion polling is aimed at sociologists, journalists, politicians, market
researchers and political analysts.
STATISTICAL INFORMATION IN EDUCATION
26-27 June 2000
Harvey Goldstein
Institute of Education, University of London
The course will look at ways in which statistical information is used in
education. It will develop ideas using two areas of topical interest:
first, research on the effects of class size on attainment; and second,
the use of comparative performances of schools on tests and examinations
to produce rankings ("league tables").
In research on class size we deal with issues of study design, especially
how to reach conclusions from both randomised and non-randomised studies.
The results of some recent data analyses will be presented and discussed.
One of the methodological issues to be addressed is the use of multilevel
models for data which have a hierarchical structure, and an introduction
to these models will be presented.
In the case of school performance indicators, there are also issues of
modelling hierarchically structured data, but especially there are issues
related to ways in which such rankings are presented. Because these issues
have become politically important in many countries, this raises interesting
points about the interface between statistical information and policy making.
These questions will be explored using databases on longitudinal achievement
from England.
Participants will be encouraged to raise problems from their own
experience, which can form the basis of group discussions.
Harvey Goldstein is Professor of Statistics at the Institute of Education,
University of London. He is the director of the project on Multilevel
Modelling, which conducts research and develops software in this area,
especially applied to educational data (see web page:
http://www.ioe.ac.uk/multilevel/).
He has published a book Multilevel Statistical Modelling, an electronic
version of which is available through his personal web page
(http://www.ioe.ac.uk/hgpersonal/index.html).
PROBABILITY AND STATISTICS FOR LAW
28 June 2000
David H. Kaye
College of Law, Arizona State University
Modern courts, lawyers, and legislators confront an enormous range of
statistical issues. In cases involving criminal prosecutions, product
liability, environmental law, antitrust enforcement, voting rights, and
discrimination, for example, crucial evidence now comes from economists,
psychologists, social scientists, epidemiologists, geneticists, and other
scientists who make use of statistical tools.
This beginning course surveys the concepts of probability theory and
statistics as they apply to the proof of facts in courts of law and in the
administrative process. It offers a basic introduction to probability,
sampling theory, descriptive statistics, regression analysis, and
statistical and causal inference. These principles are explained in
connection with such topics as the burden of persuasion in criminal and
civil cases, the definition of relevant evidence, trademark infringement,
discrimination in employment, toxicological and epidemiological proof of
causation, parentage testing, and DNA profiling. The emphasis is on ideas
rather than computation. No previous knowledge of probability or statistics
is required. The course is based on the book Prove It with Figures:
Empirical Methods in Law and Litigation (1997), by David Kaye and the late
Hans Zeisel, and on the Reference Guide on Statistics, prepared by David Kaye
and David Freedman for the U.S. Federal Judicial Center's Reference Manual on
Scientific Evidence (2000).
David Kaye is Regents' Professor, Arizona State University College of
Law. He teaches and conducts research into the law of evidence, particularly
scientific and statistical evidence. His publications include 7 books and 85
articles, reviews, or letters in journals of law, philosophy, medicine,
genetics, and statistics. He has taught or delivered invited lectures at many
universities, including Cornell, Duke and Oxford, and he has presented short
courses on statistics to judges through programs of the Federal Judicial
Center and the National Judicial College of the United States. More details
on David's web page: http://www.law.asu.edu/kaye.
STATISTICS IN POLITICAL AND SOCIAL OPINION POLLING
29-30 June 2000 (10 hours)
Nick Moon
NOP Social and Political, London
The course will briefly introduce the history of opinion polling, before
moving on to discuss the two main areas of methodological consideration:
sampling, and questionnaire design.
The sampling part of the course will discuss the relative merits of
random and quota sampling, and the ways in which they can be applied to
opinion poll design. Some examples will be given of sample designs in
practice. This discussion will cover face-to-face and telephone interviewing,
and also self-completion surveys such as postal or Web-based surveys.
The discussion of questionaire design will highlight the dangers of the
questions asked influencing the answers given. The course will also provide
a guide to assist the lay reader in interpreting polls, including examples
of common pitfalls in understanding data. While predominantly about
pre-election polling, exit polls will also be covered.
Nick Moon joined NOP as a graduate trainee in 1977, having gained a
degree in History from Cambridge, and has worked in social research for
practically his whole career. He is now manager of a team of eleven, and
although responsible for the overall direction of the Social and Political
group, works closely on surveys for much of his time. He is responsible for
NOP's considerable body of work in the field of political opinion polling,
and has a very wide range of experience of conducting social research.
For more details about NOP consult: http://www.nop.co.uk.
==========================================================================
---------------------------------------------------------
| Jan Graffelman | internet: [log in to unmask] |
| Universitat Pompeu Fabra | tel: 34-93-5421621 |
| Ramon Trias Fargas 25-27 | fax: 34-93-5421746 |
| 08005 Barcelona, Spain | |
---------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
