[ABE-L] Seminário na ENCE

[Pedro Luis do Nascimento Silva]

Caros redistas,

Dia 1 de setembro próximo o Prof. Danny Pfeffermann (Universidade de
Southampton e Hebraica de Jerusalém) fará na ENCE um seminário aberto ao
público. O Prof. Danny é um grande especialista no uso de modelos para
lidar com questões complexas de amostragem, e o evento é uma oportunidade
única para conhecer o professor e seu trabalho de pesquisa mais recente.

Mais informações conforme a chamada publicada aqui>
https://ence.ibge.gov.br/index.php/noticias/seminarios-e-defesas/1812-seminario-statistical-inference-under-nonignorable-sampling-and-nonresponse-an-empirical-likelihood-approach

Statistical Inference Under Nonignorable Sampling and Nonresponse – An
Empirical Likelihood Approach

Data: *01/09/2023 – sexta-feira*

Horário:* 10:30 horas.*

Local: *Rua André Cavalcanti, 106, sala 306 (Auditório) – ENCE
<https://ibge.webex.com/ibge/j.php?MTID=m45b8a028204c1e85bacfc743e4aa7c6b>*
*
<https://ibge.webex.com/ibge/j.php?MTID=m1cfc79a1cc66bdb8a00c68840505a261>*

Transmissão ao vivo:
*https://ibge.webex.com/ibge/j.php?MTID=m18a729d822d02605ca8e93d5e7c1fb5e
<https://ibge.webex.com/ibge/j.php?MTID=m18a729d822d02605ca8e93d5e7c1fb5e> *

Senha de acesso: *mYpTgcZP756*

*Resumo*

When the sample selection probabilities and/or the response probabilities
are related to a model outcome variable even after conditioning on the
model covariates, the model holding for the observed data is different from
the model holding in the population, resulting in biased inference if not
accounted for properly. Accounting for sample selection bias is relatively
simple because the selection probabilities are usually known. Accounting
for nonignorable non-response is much harder since the response
probabilities are generally unknown. In this article, we develop a new
approach for modelling complex survey data, which accounts simultaneously
for non-ignorable sampling and non-response. Our approach combines the
nonparametric empirical likelihood with a parametric model for the response
probabilities, which contains the outcome variable as one of the
covariates. We illustrate the robustness of the approach and propose ways
of testing the underlying model. Combining the model holding for the
responding units with the model for the response probabilities, enables
extracting the model holding for the missing data and imputing them. We
propose ways of testing the underlying model holding for the respondents’
data. Simulation results illustrate the good performance of the approach in
terms of parameter estimation and imputation. We conclude with an
application to the family expenditure survey in Israel.

*Informações:*

Tel.: 2142-4696 ou 2142-4691 e-mail: secretaria.cpgence em ibge.gov.br

*A participação é aberta a todos os docentes, alunos, funcionários do IBGE
e ao público em geral.*
-------------- Próxima Parte ----------
Um anexo em HTML foi limpo...
URL: <http://lists.ime.usp.br/pipermail/abe/attachments/20230822/0c1effaf/attachment.htm>