Re: [ABE-L]: Texto sobre pesquisa eleitoral

["Vieira M.D.T." <mdtvieira@gmail.com>]

Gostaria parabenizar os colegas José Carvalho e Cristiano pelo texto
bastante elucidativo e oportuno que, espero, possa ser um instrumento
para o inicio de um importante trabalho de conscientização das
autoridades responsáveis pela regulamentação do processo eleitoral
brasileiro.

Aproveito para enviar abaixo o resumo de uma apresentação do Professor
Fred Smith da University of Southampton, feita em 1997 em um dos
encontros da RSS.

Public Opinion Polls: The 1992 disaster and the prospects for 1997
(Joint meeting with the I.M.A.)

Abstract
The public opinion polls conducted before the 1992 general election
were a statistical disaster. The errors were far in excess of expected
sampling variation and can only be explained by biasses specific to
the context of the 1992 election since previous election results had
been forecast accurately. The replication in the polls in the months
before the election provides a natural experiment from which the
sampling variance of quota samples can be estimated. Using a
components-of-variance model, company specific variances are estimated
and are found to be consistent with those which would have been
obtained from equivalent random sample designs. Fitting time series
modelling to polling data prior to elections suggest that there is
little change in the opinions about voting in the month prior to the
election. If this is true then the need for polls to provide instant
results is less pressing. A case is made for a well-designed random
panel survey to be conducted alongside the standard quota samples used
by most polls.


Saudações,
Marcel




--
Marcel de Toledo Vieira, PhD
Professor Adjunto
Departamento de Estatística
Universidade Federal de Juiz de Fora
UFJF - Minas Gerais - Brasil
+55 32 3229 3306
http://lattes.cnpq.br/1980385021266418