Avviso di Seminari

[andrea.ongaro@unimib.it (Ongaro Andrea - Dip. di Statistica)]

Nei giorni 22 - 25 Settembre 2003 il

                              PROF. J.N.K. RAO
                  Carleton University, Ottawa, Canada

sarā ospite del Dipartimento di Statistica,  Universitā di Milano-Bicocca.
Durante la sua visita il Prof.  Rao terrā  il corso breve:

         SMALL AREA ESTIMATION: METHODS AND APPLICATIONS

Il corso, rivolto a Dottorandi, Ricercatori ed a tutti gli interessati, si
svolgerā presso l'Aula Tesi della Facoltā di Scienze Statistiche, Via
Bicocca degli Arcimboldi, 8, 20126 Milano, Edificio U7, II piano, con
i seguenti orari:

23.9.2003	h. 10:30 - 12:30
24.9.2003	h. 14:00 - 16:00
25.9.2003	h. 10:30 - 12:30

Per ulteriori informazioni: fulvia.mecatti@unimib.it

                              ABSTRACT

Small area estimation has received a lot of attention in recent years due
to growing demand for reliable small area statistics that are needed in
formulating policies and programs, allocation of funds, regional planning
and market research. Sample sizes in small areas are typically small.
As a result, customary direct estimators based on area-specific sample data
do not provide acceptable quality in terms of MSE. Indirect estimators that
improve efficiency by borrowing strength from related areas through linking
models based on auxiliary data (such as census and administrative data) are
therefore now widely used for small area estimation. Such linking models
are either implicit (as in the case of traditional synthetic estimators) or
explicit (as in the case of model based indirect estimators). Two approaches
are commonly used for making inferences for small areas: frequentist and
hierarchical Bayes. In the frequentist approach, the quality of an indirect
estimator is measured by its estimated MSE while in the hierarchical Bayes
approach posterior variance is used. In the three lectures, I will review
developments in small area indirect estimation and estimating MSE and
evaluating posterior variance using Monte Carlo Markov chain methods.
I will also discuss methods for model checking and validation. Several
applications of indirect estimation will also be presented.


                     BIO-SKETCH of J. N. K. RAO

J. N. K. Rao is Professor Emeritus and Distinguished Research Professor at
Carleton University. He is also a consultant to Statistics Canada on survey
methodology since 1974 and he is a member of the advisory board on survey
methodology. He served as a member of the Panel on Estimates of Poverty for
Small Geographic Areas, Committee on National Statistics, USA. His primary
research interests are in sample survey theory and methodology, particularly
the analysis of complex survey data, small area estimation and inference
under imputation for missing data. He has published extensively in these areas
as well as in linear models, time series analysis and bio-statistics. He has
published a Wiley book Small Area Estimation in 2003. His 1981 joint paper
on the analysis of categorical survey data published in the Journal of the
American Statistical Association has been selected as a landmark paper in
survey statistics covering the period 1934-1990. He has received many
professional honors including the following: Fellow of the Royal Society of
Canada, Fellow of the American Statistical Association, Fellow of the
Institute of Mathematical Statistics, Fellow of the American Association
for the Advancement of Science, the 1993 Gold Medal of the Statistical
Society of Canada for outstanding research achievements, Program Chair of
the International Statistical Institute Meetings in 1999.. He has served as
Associate Editor for several journals including the Annals of Statistics, 
Journal
of the American Statistical Association, Survey Methodology, Statistica
Sinica and Journal of Statistical Planning and Inference.