In this talk we deal with model assessment, estimation, and hypothesis testing in a linear functional relationship for replicated data when the distribution of the measurement errors is the multivariate Student t distribution. Inference is based on the unbiased estimating equations approach. A simple graphical device for model checking is proposed. We also describe how to test some hypotheses of interest on the parameter vector using the Wald statistic. A simulation study is carried out to assess the performance of the estimators and of the Wald statistic. The methodology is applied in the analysis of a data set on measurement methods comparison.
Professor associado do Instituto de Ciências Matemáticas e de Computação da Universidade de São Paulo. Desenvolve trabalhos em modelos com erros de medição, análise de sobrevivência e modelos para dados de contagem.
Joint work with Manuel Galea (PUC de Chile, Santiago, Chile)