Overweight and obesity related factors in schoolchildren in Santa Catarina State, Brazil

The purpose of this study is to determine the correlation of socioeconomic, dietary, and anthropometric-nutritional variables of parents and their children to overweight (including obesity) in schoolchildren in Santa Catarina State, Brazil. This is a transversal study conducted on 4,964, 6 to 10-year-old schoolchildren registered in 345 Santa Catarina elementary schools. The following data were acquired: the children`s current weight and height, birth weight and length, duration of breastfeeding, age at which water, herbal tea and other foods were introduced to their diet; parental income, education level, age, weight and height were also obtained. The prevalence of overweight and obese children were estimated by point and by interval with a 95% confidence; prevalence rates were obtained based on the Poisson model. An hierarchical approach was used, in which variables were adjusted within blocks and included in the model when they presented p<0.05 at the outcome (overweight including obesity). The results indicate that 47.8% of the subjects were male. The prevalence of overweight and obese students was 15.4% (C195%: 14.4%-16.5%) and 6.1% (CI95%: 5.4%-6.7%) respectively and were statistically similar among sexes and age ranges. BMI values were higher in males and among older children (p<0.05). After adjustment within and among blocks, the variables per capita household income and parents` BM I values remained associated with overweight (including obesity). Overweight (including obesity) in schoolchildren is associated with a higher per capita household income and parental overweight and obesity.

Likelihood ratio tests for variance components in linear mixed models

Although the asymptotic distributions of the likelihood ratio for testing hypotheses of null variance components in linear mixed models derived by Stram and Lee [1994. Variance components testing in longitudinal mixed effects model. Biometrics 50, 1171-1177] are valid, their proof is based on the work of Self and Liang [1987. Asymptotic properties of maximum likelihood estimators and likelihood tests under nonstandard conditions. J. Amer. Statist. Assoc. 82, 605-610] which requires identically distributed random variables, an assumption not always valid in longitudinal data problems. We use the less restrictive results of Vu and Zhou [1997. Generalization of likelihood ratio tests under nonstandard conditions. Ann. Statist. 25, 897-916] to prove that the proposed mixture of chi-squared distributions is the actual asymptotic distribution of such likelihood ratios used as test statistics for null variance components in models with one or two random effects. We also consider a limited simulation study to evaluate the appropriateness of the asymptotic distribution of such likelihood ratios in moderately sized samples. (C) 2008 Elsevier B.V. All rights reserved.