This file is part of IDEAS, which uses RePEc data


[ Papers | Articles | Software | Books | Chapters | Authors | Institutions | JEL Classification | NEP reports | Search | New papers by email | Author registration | Rankings | Volunteers | FAQ | Blog | Help! ]

O Atrito nas Pesquisas Longitudinais: O Caso da Pesquisa Mensal de EMPREGO (PME) do IBGE

Author info | Abstract | Publisher info | Download info | Related research | Statistics
Author Info
Rafael Perez Ribas
Sergei Suarez Dillon Soares

Additional information is available for the following registered author(s):

Abstract

O objetivo deste artigo é estimar os determinantes do atrito/permanência de pessoas no painel da Pesquisa Mensal de Emprego (PME), do Instituto Brasileiro de Geografia e Estatística (IBGE) e, além disso, testar se ignorar a não-aleatoriedade deste desgaste causa algum viés na análise de regressões. O atrito pode ser de três tipos: a) aleatório, que não gera qualquer tipo de viés em estimações de parâmetros; b) função de variáveis observadas, cujo viés pode ser corrigido mediante repesagem adequada; e c) função de variáveis não-observadas, cujo viés pode ser corrigido usando-se um probit bivariado para variáveis discretas ou a correção de Heckman para variáveis contínuas. Os resultados apontam que a taxa de atrito na pesquisa tende a ser maior nos meses de férias, e que há uma forte correlação dessa taxa com as características geralmente associadas a uma mobilidade geográfica maior. Além disso, tanto características do processo de entrevista quanto fatores socioeconômicos são significativamente relacionados à probabilidade de atrito no painel. Nos modelos adotados para testar o viés do desgaste no painel, assim como de outros critérios de seleção amostral, constatamos que todos estes são endógenos, apesar de alguns não estarem diretamente correlacionados com a equação de interesse. Por fim, mostramos que a ausência do controle para seleção amostral, o que inclui a retenção no painel, pode incorrer em algumas análises enviesadas. Contudo, a inclusão do controle para somente alguns mecanismos de seleção pode fornecer estatísticas ainda mais inconsistentes do que se não fosse incluído nenhum mecanismo. Our objective is to analyze the gravity of panel attrition in the Brazilian Monthly Employment Survey (PME). There are three types of panel attrition: a) random, that does not produce any selection bias; b) function of observables, whose bias can be corrected through an appropriate re-weighing scheme; and c) function of unobservable variables, whose bias can be corrected through a bivariate probit for discrete variables or a Heckman correction for continuous ones. To test the gravity of panel attrition bias we estimated a transition to unemployment model both with and without attrition bias controls. Our results are that attrition tends to increase during school vacations and that attrition is strongly correlated to geographical mobility. Our conclusion is that while attrition bias does exist, its magnitude is small and its elimination does not substantially change analysis made using the models. In addition, in some cases, since it is not possible to control simultaneously for observable and non-observable attrition bias, in some cases the best procedure is not use on controls at all.

Download Info
To download:

If you experience problems downloading a file, check if you have the proper application to view it first. Information about this may be contained in the File-Format links below. In case of further problems read the IDEAS help page. Note that these files are not on the IDEAS site. Please be patient as the files may be large.

File URL: http://www.ipea.gov.br/sites/000/2/publicacoes/tds/td_1347.pdf
File Format: application/pdf
File Function:
Download Restriction: no

Publisher Info
Paper provided by Instituto de Pesquisa Econômica Aplicada - IPEA in its series Discussion Papers with number 1347.

Download reference. The following formats are available: HTML (with abstract), plain text (with abstract), BibTeX, RIS (EndNote, RefMan, ProCite), ReDIF
Length: 39 pages
Date of creation: Aug 2008
Date of revision:
Handle: RePEc:ipe:ipetds:1347

Contact details of provider:
Postal: SBS - Quadra 01 - Bloco J - Ed. BNDES, Bras�lia, DF - 70076-90
Phone: +55(061)315-5000
Fax: +55(61)321-1597
Email:
Web page: http://www.ipea.gov.br
More information through EDIRC

For technical questions regarding this item, or to correct its listing, contact: (Fabio Schiavinatto).

Related research
Keywords:

This paper has been announced in the following NEP Reports:

Statistics
Access and download statistics

Did you know? All the bibliographic data shown here has been contributed by volunteers, thereby helping to keep this service free.

This page was last updated on 2009-11-25.


This information is provided to you by IDEAS at the Department of Economics, College of Liberal Arts and Sciences, University of Connecticut using RePEc data on a server sponsored by the Society for Economic Dynamics.