Gilenio Borges Fernandes

Indicadores antropométricos na predição de síndrome metabólica em crianças e adolescentes: um estudo de base populacional

Objectives: to assess the capacity of anthropometric indicators to predict metabolic syndrome in children and adolescents and to establish cut-off points. Methods: a cross-sectional study was carried out with a probabilistic sample of 879 children and adolescents of both sexes. Metabolic, anthropometric and socio-demographic data were gathered. Diagnosis of metabolic syndrome was carried out using the modified definition of the National Cholesterol Education Program s Adult Treatment Panel III (NCEP-ATPIII). The capacity of anthropometric indicators to predict metabolic syndrome was assessed using the Receiver Operating Characteristic (ROC) curve. Results: the prevalence of metabolic syndrome was 6.6%. For prediction of metabolic syndrome, the area under the ROC curve was 0. 79 (0. 72; 0.85) for body mass index, 0. 79 (0.73; 0.85) for waist circumference and 0.83 (0.78; 0.89) for waist circumference corrected for height. The cut-off point identified for waist circumference corrected for height for prediction of metabolic syndrome was 0.448 (for both sexes). Conclusions: all anthropometric indicators used were good predictors of metabolic syndrome, with slightly better results for waist circumference corrected for height. The cut-off point identified for waist circumference corrected for height for prediction of metabolic syndrome was similar to the standard proposed by other authors. It is suggested that this indicator be used in clinical and epidemiological studies as a predictor of metabolic syndrome, since it is simple to measure.

Heteroskedasticity-Robust Inference in Linear Regressions

The assumption that all errors share the same variance (homoskedasticity) is commonly violated in empirical analyses carried out using the linear regression model. A widely adopted modeling strategy is to perform point estimation by ordinary least squares and then perform testing inference based on these point estimators and heteroskedasticity-consistent standard errors. These tests, however, tend to be size-distorted when the sample size is small and the data contain atypical observations. Furno (1996) suggested performing point estimation using a weighted least squares mechanism in order to attenuate the effect of leverage points on the associated inference. In this article, we follow up on her proposal and define heteroskedasticity-consistent covariance matrix estimators based on residuals obtained using robust estimation methods. We report Monte Carlo simulation results (size and power) on the finite sample performance of different heteroskedasticity-robust tests. Overall, the results favor inference based on HC0 tests constructed using robust residuals.