[Multiple imputations for missing data: a simulation with epidemiological data].
TL;DR: In this article, a trabalho em situacoes com dados faltantes, e comum restringir-se a analise dos sujeitos com dads completos, is presented.
read more
Abstract: Em situacoes com dados faltantes, e comum restringir-se a analise dos sujeitos com dados completos. Porem, as estimativas com apenas esses sujeitos podem tornar-se viesadas. A pratica de preenchimento de dados faltantes e a chamada tecnica de imputacao. Este trabalho tem como objetivo divulgar o metodo de imputacao multipla. Em um conjunto de dados de 470 pacientes cirurgicos, foram ajustados modelos logisticos para o desfecho obito. Foram gerados dois conjuntos de dados incompletos: um com 5% e outro com 20% de dados faltantes para uma variavel. Foram ajustados modelos para o conjunto completo, com dados faltantes e para o conjunto completado por imputacao multipla. As estimativas obtidas pela analise dos conjuntos com dados faltantes e com o conjunto completo foram diferentes, principalmente as do conjunto com 20% de dados faltantes. A imputacao multipla utilizada pareceu eficiente, pois os resultados conseguidos com o banco completado por imputacoes foram proximos dos obtidos com o conjunto completo. Porem, um coeficiente deixou de ser estatisticamente significativo. A imputacao multipla se mostrou superior a analise do conjunto com dados faltantes, que desconsiderou os casos incompletos.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Multiple Imputation for Nonresponse in Surveys
TL;DR: It is concluded that multiple Imputation for Nonresponse in Surveys should be considered as a legitimate method for answering the question of why people do not respond to survey questions.
3.5K
Sociodemographic and behavioral factors associated with physical activity in Brazilian adolescents
Leandro Fórnias Machado de Rezende,Catarina Machado Azeredo,Daniela Silva Canella,Rafael Moreira Claro,Inês Rugani Ribeiro de Castro,Renata Bertazzi Levy,Olinda do Carmo Luiz +6 more
TL;DR: The physical activity of Brazilian adolescents in physical education classes, during leisure time, and during active commuting is described and the socio-demographic and behavioral factors associated with physical activity are investigated.
Prevalência e fatores associados ao diagnóstico de câncer de mama em estágio avançado
Tainá Bastos dos Santos,Anne Karin da Mota Borges,Jeniffer Dantas Ferreira,Karina Cardoso Meira,Mirian de Souza,Raphael Mendonça Guimarães,Rafael Tavares Jomar +6 more
TL;DR: In this paper , the authors investigate prevalência e fatores associated with the diagnóstico de câncer de mama in a population of 18.890 women.
38
Multiple imputation and complete case analysis in logistic regression models: a practical assessment of the impact of incomplete covariate data
Vitor Passos Camargos,Cibele Comini César,Waleska Teixeira Caiaffa,César Coelho Xavier,Fernando Augusto Proietti +4 more
TL;DR: Data from the study Saúde em Beagá, attended by 4,048 adults from two of nine health districts in the city of Belo Horizonte, Minas Gerais State, Brazil, in 2008-2009 were used to evaluate CCA and different MI approaches in the context of logistic models with incomplete covariate data.
Comparison of simple and multiple imputation methods using a risk model for surgical mortality as example
TL;DR: The results indicate that it is important to take into account the relationship of albumin to other variables observed, because different models were obtained in single and multiple imputations, and single imputation underestimates the variability generating narrower confidence intervals.
References
mice: Multivariate Imputation by Chained Equations in R
TL;DR: Mice adds new functionality for imputing multilevel data, automatic predictor selection, data handling, post-processing imputed values, specialized pooling routines, model selection tools, and diagnostic graphs.
Missing data: Our view of the state of the art.
Joseph L. Schafer,John W. Graham +1 more
TL;DR: 2 general approaches that come highly recommended: maximum likelihood (ML) and Bayesian multiple imputation (MI) are presented and may eventually extend the ML and MI methods that currently represent the state of the art.
Regression Modeling Strategies: With Applications to Linear Models, Logistic Regression, and Survival Analysis
TL;DR: The basic Bayesian framework must be constrained, use of the step function in computing the probability that a team would rank best or worst in a league, and implementation of a Dirichlet process prior are presented.
5.2K
Multiple imputation: a primer:
TL;DR: Essential features of multiple imputation are reviewed, with answers to frequently asked questions about using the method in practice.
3.8K
Multiple Imputation After 18+ Years
TL;DR: A description of the assumed context and objectives of multiple imputation is provided, and a review of the multiple imputations framework and its standard results are reviewed.